diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/01ba63fe8fbad8372970aae6948ad666bd011b8974ec889b521941bc8ec8e277/065fd827ba7bdb1b7c59.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/01ba63fe8fbad8372970aae6948ad666bd011b8974ec889b521941bc8ec8e277/065fd827ba7bdb1b7c59.json new file mode 100644 index 0000000000000000000000000000000000000000..43b367faf2d6b0ea8264c1f8320b704913318121 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/01ba63fe8fbad8372970aae6948ad666bd011b8974ec889b521941bc8ec8e277/065fd827ba7bdb1b7c59.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RobertaModel", + "_task": "token-classification", + "add_cross_attention": false, + "architectures": [ + "RobertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1024 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0423a3e7d8c645ee4d3e9212c291d4898394fa162afd4caf9a8d0fffb8d25ae9/23b06fee742b8d52b152.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0423a3e7d8c645ee4d3e9212c291d4898394fa162afd4caf9a8d0fffb8d25ae9/23b06fee742b8d52b152.json new file mode 100644 index 0000000000000000000000000000000000000000..4fc29e5eb315d2e2a48ecc93ae155e0f6e45e531 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0423a3e7d8c645ee4d3e9212c291d4898394fa162afd4caf9a8d0fffb8d25ae9/23b06fee742b8d52b152.json @@ -0,0 +1,46 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "text-classification", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0426f0caf9933a9072214e0e87f1c0f08b4c94c01b52d6cfa810ce61b4918593/ab8896ff9f6498094b99.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0426f0caf9933a9072214e0e87f1c0f08b4c94c01b52d6cfa810ce61b4918593/ab8896ff9f6498094b99.json new file mode 100644 index 0000000000000000000000000000000000000000..5ee150120ec58240a9ebb29ce8f07da3ffac0227 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0426f0caf9933a9072214e0e87f1c0f08b4c94c01b52d6cfa810ce61b4918593/ab8896ff9f6498094b99.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MobileBertModel", + "_task": "token-classification", + "architectures": [ + "MobileBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_activation": true, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 37, + "intra_bottleneck_size": 128, + "key_query_shared_bottleneck": true, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mobilebert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mobilebert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "normalization_type": "no_norm", + "num_attention_heads": 4, + "num_feedforward_networks": 4, + "num_hidden_layers": 5, + "tie_word_embeddings": true, + "trigram_input": true, + "true_hidden_size": 128, + "type_vocab_size": 16, + "use_bottleneck": true, + "use_bottleneck_attention": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/08a7df94dccea09e0d94a3cf6a30d5b4849e3be1c8583bc9a881911f3a7d32a1/54a74c2bb8ecb10d9ed4.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/08a7df94dccea09e0d94a3cf6a30d5b4849e3be1c8583bc9a881911f3a7d32a1/54a74c2bb8ecb10d9ed4.json new file mode 100644 index 0000000000000000000000000000000000000000..4fce86796b433730272fb8ebe5ea7de88ecd5d61 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/08a7df94dccea09e0d94a3cf6a30d5b4849e3be1c8583bc9a881911f3a7d32a1/54a74c2bb8ecb10d9ed4.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DistilBertModel", + "_task": "fill-mask", + "activation": "gelu", + "architectures": [ + "DistilBertModel" + ], + "attention_dropout": 0.1, + "dim": 32, + "dropout": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dim": 37, + "initializer_range": 0.02, + "max_position_embeddings": 512, + "model_type": "distilbert", + "n_heads": 4, + "n_layers": 5, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "distilbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "qa_dropout": 0.1, + "seq_classif_dropout": 0.2, + "sinusoidal_pos_embds": false, + "tie_word_embeddings": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/08a7df94dccea09e0d94a3cf6a30d5b4849e3be1c8583bc9a881911f3a7d32a1/fd9b9742ee90f2a3f4a6.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/08a7df94dccea09e0d94a3cf6a30d5b4849e3be1c8583bc9a881911f3a7d32a1/fd9b9742ee90f2a3f4a6.json new file mode 100644 index 0000000000000000000000000000000000000000..bd3752fed263fceae03d3e0153f5a84ca4a8715b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/08a7df94dccea09e0d94a3cf6a30d5b4849e3be1c8583bc9a881911f3a7d32a1/fd9b9742ee90f2a3f4a6.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DistilBertModel", + "_task": "fill-mask", + "activation": "gelu", + "architectures": [ + "DistilBertModel" + ], + "attention_dropout": 0.1, + "dim": 32, + "dropout": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dim": 37, + "initializer_range": 0.02, + "max_position_embeddings": 512, + "model_type": "distilbert", + "n_heads": 4, + "n_layers": 5, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "distilbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "qa_dropout": 0.1, + "seq_classif_dropout": 0.2, + "sinusoidal_pos_embds": false, + "tie_word_embeddings": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/08aedcd80b6757e8054dba5f358d146341ce9ce242f865d28d985547ed955b0b/c805a16a5ea184c3dd6a.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/08aedcd80b6757e8054dba5f358d146341ce9ce242f865d28d985547ed955b0b/c805a16a5ea184c3dd6a.json new file mode 100644 index 0000000000000000000000000000000000000000..75788f5f94e4975cf90a6da8870ea02a7cc705e9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/08aedcd80b6757e8054dba5f358d146341ce9ce242f865d28d985547ed955b0b/c805a16a5ea184c3dd6a.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "token-classification", + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/09ed50c44c029ada88e0af27afe057553066c260b0f1004a82f2d44e64165b17/cafe82ab9aa2ab7a8a6a.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/09ed50c44c029ada88e0af27afe057553066c260b0f1004a82f2d44e64165b17/cafe82ab9aa2ab7a8a6a.json new file mode 100644 index 0000000000000000000000000000000000000000..3a6056e3c1b9234aa9ef0dd9b93452453b936221 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/09ed50c44c029ada88e0af27afe057553066c260b0f1004a82f2d44e64165b17/cafe82ab9aa2ab7a8a6a.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RoFormerModel", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "RoFormerModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roformer", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roformer", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "rotary_value": false, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 50000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0d0b05c409ee9e0c6bafa2d9d6be5147761b1582b056f2af3ae3e87b99cbbeff/dad1996ab0ffa855bcc4.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0d0b05c409ee9e0c6bafa2d9d6be5147761b1582b056f2af3ae3e87b99cbbeff/dad1996ab0ffa855bcc4.json new file mode 100644 index 0000000000000000000000000000000000000000..f68cf438bf4633c543e2a038f97ba622c74c8886 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0d0b05c409ee9e0c6bafa2d9d6be5147761b1582b056f2af3ae3e87b99cbbeff/dad1996ab0ffa855bcc4.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MobileBertModel", + "_task": "feature-extraction", + "architectures": [ + "MobileBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_activation": true, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 37, + "intra_bottleneck_size": 128, + "key_query_shared_bottleneck": true, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mobilebert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mobilebert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "normalization_type": "no_norm", + "num_attention_heads": 4, + "num_feedforward_networks": 4, + "num_hidden_layers": 5, + "trigram_input": true, + "true_hidden_size": 128, + "type_vocab_size": 16, + "use_bottleneck": true, + "use_bottleneck_attention": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0dac283aca5002a059842e78dc2ef030f4e3b9b3c26ef670bc1d758214f256f4/0b8be8f701e2def700f8.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0dac283aca5002a059842e78dc2ef030f4e3b9b3c26ef670bc1d758214f256f4/0b8be8f701e2def700f8.json new file mode 100644 index 0000000000000000000000000000000000000000..1a4f3259c219dcb07ffd7d2fe5f21471397cc970 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0dac283aca5002a059842e78dc2ef030f4e3b9b3c26ef670bc1d758214f256f4/0b8be8f701e2def700f8.json @@ -0,0 +1,61 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-XLMModel", + "_task": "token-classification", + "architectures": [ + "XLMModel" + ], + "asm": false, + "attention_dropout": 0.1, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "mask_index": 5, + "mask_token_id": 5, + "max_position_embeddings": 512, + "model_type": "xlm", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "xlm", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "tie_word_embeddings": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": true, + "vocab_size": 30145 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0ec3edee969c7993223e4436830b3fae2760e33e798abbabc581282a5feec254/4eb80a86f3750d9d483d.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0ec3edee969c7993223e4436830b3fae2760e33e798abbabc581282a5feec254/4eb80a86f3750d9d483d.json new file mode 100644 index 0000000000000000000000000000000000000000..0f61e5f32916d28f7492780ae546ad2fee14f95d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0ec3edee969c7993223e4436830b3fae2760e33e798abbabc581282a5feec254/4eb80a86f3750d9d483d.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RoFormerModel", + "_task": "fill-mask", + "add_cross_attention": false, + "architectures": [ + "RoFormerModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roformer", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roformer", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "rotary_value": false, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 50000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0ec3edee969c7993223e4436830b3fae2760e33e798abbabc581282a5feec254/abafbbe84ebc6e15e836.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0ec3edee969c7993223e4436830b3fae2760e33e798abbabc581282a5feec254/abafbbe84ebc6e15e836.json new file mode 100644 index 0000000000000000000000000000000000000000..171c4feb096824acf52d7bd3c42160110a8ab651 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0ec3edee969c7993223e4436830b3fae2760e33e798abbabc581282a5feec254/abafbbe84ebc6e15e836.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RoFormerModel", + "_task": "fill-mask", + "add_cross_attention": false, + "architectures": [ + "RoFormerModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roformer", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roformer", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "rotary_value": false, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 50000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0fc56309d64256371e7ed32dfbb1e1ad7d495051a0b5750770574ae275fa2bf6/ee4fc48e52b39ca7deba.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0fc56309d64256371e7ed32dfbb1e1ad7d495051a0b5750770574ae275fa2bf6/ee4fc48e52b39ca7deba.json new file mode 100644 index 0000000000000000000000000000000000000000..f0329bbcfe3a31e2bd8436293603530fa642fc32 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0fc56309d64256371e7ed32dfbb1e1ad7d495051a0b5750770574ae275fa2bf6/ee4fc48e52b39ca7deba.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-flaubert", + "_task": "token-classification", + "architectures": [ + "FlaubertModel" + ], + "asm": false, + "attention_dropout": 0.1, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "layerdrop": 0.0, + "mask_index": 5, + "mask_token_id": 0, + "max_position_embeddings": 512, + "model_type": "flaubert", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "flaubert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "pre_norm": false, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "tie_word_embeddings": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": null, + "vocab_size": 68729 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/10fbb7a32daf017df676ae756b2012e50d92e6e9fcc9f382e03e980b2ac64c8b/0fca3e04298ddbbf44ec.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/10fbb7a32daf017df676ae756b2012e50d92e6e9fcc9f382e03e980b2ac64c8b/0fca3e04298ddbbf44ec.json new file mode 100644 index 0000000000000000000000000000000000000000..d3237331de63ff062bb3fba62159c699edbe9257 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/10fbb7a32daf017df676ae756b2012e50d92e6e9fcc9f382e03e980b2ac64c8b/0fca3e04298ddbbf44ec.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DebertaV2Model", + "_task": "fill-mask", + "architectures": [ + "DebertaV2Model" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-07, + "legacy": true, + "max_position_embeddings": 512, + "max_relative_positions": -1, + "model_type": "deberta-v2", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "deberta-v2", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "pooler_dropout": 0, + "pooler_hidden_act": "gelu", + "pooler_hidden_size": 32, + "pos_att_type": [ + "none" + ], + "position_biased_input": true, + "relative_attention": false, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 128001 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/13739f6d106c0739b7b650b2749aeb53dad2442987221bb77338be7b9706561e/3a21bb8958d3001988d8.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/13739f6d106c0739b7b650b2749aeb53dad2442987221bb77338be7b9706561e/3a21bb8958d3001988d8.json new file mode 100644 index 0000000000000000000000000000000000000000..ab22e1159a68d8f9baa293b9ff2b3fc33cc22ef6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/13739f6d106c0739b7b650b2749aeb53dad2442987221bb77338be7b9706561e/3a21bb8958d3001988d8.json @@ -0,0 +1,46 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "token-classification", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/15caa5bbbdee4a746804162c591c1ead872bb24243455826856391594a1cdd7b/a1fa39f3b67695d6132f.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/15caa5bbbdee4a746804162c591c1ead872bb24243455826856391594a1cdd7b/a1fa39f3b67695d6132f.json new file mode 100644 index 0000000000000000000000000000000000000000..5267681df0ef17435db267225dfb226bbf36d7dd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/15caa5bbbdee4a746804162c591c1ead872bb24243455826856391594a1cdd7b/a1fa39f3b67695d6132f.json @@ -0,0 +1,127 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-4", + "_task": "text-generation", + "architectures": [ + "Llama4ForConditionalGeneration" + ], + "boi_token_index": 200080, + "dtype": "float32", + "eoi_token_index": 200081, + "image_token_index": 200092, + "model_type": "llama4", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-4", + "checkpoint_revision": "40216585996ab548819dea4cd1d46e0c0c1093d9", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "text_config": { + "_attn_implementation_autoset": true, + "attention_bias": false, + "attention_chunk_size": 8192, + "attention_dropout": 0.0, + "attn_scale": 0.1, + "attn_temperature_tuning": true, + "bos_token_id": 1, + "dtype": "float32", + "eos_token_id": 2, + "floor_scale": 8192, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 512, + "initializer_range": 0.02, + "interleave_moe_layer_step": 1, + "intermediate_size": 1024, + "intermediate_size_mlp": 1024, + "layer_types": [ + "chunked_attention", + "chunked_attention", + "chunked_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "model_type": "llama4_text", + "moe_layers": [ + 0, + 1, + 2, + 3 + ], + "no_rope_layer_interval": 4, + "no_rope_layers": [ + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 8, + "num_experts_per_tok": 1, + "num_hidden_layers": 4, + "num_key_value_heads": 2, + "num_local_experts": 2, + "output_router_logits": false, + "pad_token_id": null, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "rope_theta": 500000, + "rope_type": "default" + }, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "tie_word_embeddings": false, + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 202048 + }, + "tie_word_embeddings": false, + "vision_config": { + "_attn_implementation_autoset": true, + "attention_dropout": 0.0, + "hidden_act": "gelu", + "hidden_size": 1408, + "image_size": 336, + "initializer_range": 0.02, + "intermediate_size": 5632, + "model_type": "llama4_vision_model", + "multi_modal_projector_bias": false, + "norm_eps": 1e-05, + "num_attention_heads": 16, + "num_channels": 3, + "num_hidden_layers": 4, + "patch_size": 14, + "pixel_shuffle_ratio": 0.5, + "projector_dropout": 0.0, + "projector_input_dim": 4096, + "projector_output_dim": 4096, + "rope_parameters": { + "rope_theta": 10000, + "rope_type": "default" + }, + "vision_feature_layer": -1, + "vision_feature_select_strategy": "default", + "vision_output_dim": 4096 + } +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/15d4636f2b7fd3439362bdf2793d11cc88bcba5bd44adb1b3f0e8fc9480f9ec9/18ff55daef0c05569b98.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/15d4636f2b7fd3439362bdf2793d11cc88bcba5bd44adb1b3f0e8fc9480f9ec9/18ff55daef0c05569b98.json new file mode 100644 index 0000000000000000000000000000000000000000..14852cbc2a3cc6aa8ae527f75cc1987023de02ac --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/15d4636f2b7fd3439362bdf2793d11cc88bcba5bd44adb1b3f0e8fc9480f9ec9/18ff55daef0c05569b98.json @@ -0,0 +1,105 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-Wav2Vec2Model", + "_task": "audio-frame-classification", + "activation_dropout": 0.1, + "adapter_attn_dim": null, + "adapter_kernel_size": 3, + "adapter_stride": 2, + "add_adapter": false, + "apply_spec_augment": true, + "architectures": [ + "Wav2Vec2Model" + ], + "attention_dropout": 0.1, + "classifier_proj_size": 256, + "codevector_dim": 256, + "contrastive_logits_temperature": 0.1, + "conv_bias": false, + "conv_dim": [ + 32, + 32, + 32 + ], + "conv_kernel": [ + 8, + 8, + 8 + ], + "conv_stride": [ + 4, + 4, + 4 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "diversity_loss_weight": 0.1, + "do_stable_layer_norm": false, + "dtype": "float32", + "feat_extract_activation": "gelu", + "feat_extract_dropout": 0.0, + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_quantizer_dropout": 0.0, + "final_dropout": 0.1, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_dropout_prob": 0.1, + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 20, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 2, + "mask_time_min_masks": 2, + "mask_time_prob": 0.5, + "model_type": "wav2vec2", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "wav2vec2", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_audio_sequence_length": 100000, + "static_batch_size": 1, + "task": "audio-frame-classification", + "tensor_parallel_size": 1 + }, + "num_adapter_layers": 1, + "num_attention_heads": 2, + "num_codevector_groups": 2, + "num_codevectors_per_group": 320, + "num_conv_pos_embedding_groups": 2, + "num_conv_pos_embeddings": 16, + "num_feat_extract_layers": 3, + "num_hidden_layers": 4, + "num_negatives": 100, + "output_hidden_size": 16, + "proj_codevector_dim": 256, + "tdnn_dilation": [ + 1, + 2 + ], + "tdnn_dim": [ + 32, + 32 + ], + "tdnn_kernel": [ + 5, + 3 + ], + "use_weighted_layer_sum": false, + "vocab_size": 32, + "xvector_output_dim": 32 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/15d4636f2b7fd3439362bdf2793d11cc88bcba5bd44adb1b3f0e8fc9480f9ec9/65b7e85920a69446bf5d.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/15d4636f2b7fd3439362bdf2793d11cc88bcba5bd44adb1b3f0e8fc9480f9ec9/65b7e85920a69446bf5d.json new file mode 100644 index 0000000000000000000000000000000000000000..9ca90a6bc9e31fd2b83cfe0bc3f1843e28c3e649 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/15d4636f2b7fd3439362bdf2793d11cc88bcba5bd44adb1b3f0e8fc9480f9ec9/65b7e85920a69446bf5d.json @@ -0,0 +1,105 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-Wav2Vec2Model", + "_task": "audio-frame-classification", + "activation_dropout": 0.1, + "adapter_attn_dim": null, + "adapter_kernel_size": 3, + "adapter_stride": 2, + "add_adapter": false, + "apply_spec_augment": true, + "architectures": [ + "Wav2Vec2Model" + ], + "attention_dropout": 0.1, + "classifier_proj_size": 256, + "codevector_dim": 256, + "contrastive_logits_temperature": 0.1, + "conv_bias": false, + "conv_dim": [ + 32, + 32, + 32 + ], + "conv_kernel": [ + 8, + 8, + 8 + ], + "conv_stride": [ + 4, + 4, + 4 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "diversity_loss_weight": 0.1, + "do_stable_layer_norm": false, + "dtype": "float32", + "feat_extract_activation": "gelu", + "feat_extract_dropout": 0.0, + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_quantizer_dropout": 0.0, + "final_dropout": 0.1, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_dropout_prob": 0.1, + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 20, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 2, + "mask_time_min_masks": 2, + "mask_time_prob": 0.5, + "model_type": "wav2vec2", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "wav2vec2", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_audio_sequence_length": 100000, + "static_batch_size": 1, + "task": "audio-frame-classification", + "tensor_parallel_size": 1 + }, + "num_adapter_layers": 1, + "num_attention_heads": 2, + "num_codevector_groups": 2, + "num_codevectors_per_group": 320, + "num_conv_pos_embedding_groups": 2, + "num_conv_pos_embeddings": 16, + "num_feat_extract_layers": 3, + "num_hidden_layers": 4, + "num_negatives": 100, + "output_hidden_size": 16, + "proj_codevector_dim": 256, + "tdnn_dilation": [ + 1, + 2 + ], + "tdnn_dim": [ + 32, + 32 + ], + "tdnn_kernel": [ + 5, + 3 + ], + "use_weighted_layer_sum": false, + "vocab_size": 32, + "xvector_output_dim": 32 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/164c2b66672307ef2b43fee228f4b796bce44963a6b1758f39864522a9ba7fad/9a41e8abebe9fe39bc3e.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/164c2b66672307ef2b43fee228f4b796bce44963a6b1758f39864522a9ba7fad/9a41e8abebe9fe39bc3e.json new file mode 100644 index 0000000000000000000000000000000000000000..db55b5181d4ed6a7df608942ab162fbddc115e53 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/164c2b66672307ef2b43fee228f4b796bce44963a6b1758f39864522a9ba7fad/9a41e8abebe9fe39bc3e.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RoFormerModel", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "RoFormerModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roformer", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roformer", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "rotary_value": false, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 50000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/164c2b66672307ef2b43fee228f4b796bce44963a6b1758f39864522a9ba7fad/e45115884180009d7fd5.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/164c2b66672307ef2b43fee228f4b796bce44963a6b1758f39864522a9ba7fad/e45115884180009d7fd5.json new file mode 100644 index 0000000000000000000000000000000000000000..30e19e95c9362dacf13bbe3487c22c313e85f4a4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/164c2b66672307ef2b43fee228f4b796bce44963a6b1758f39864522a9ba7fad/e45115884180009d7fd5.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RoFormerModel", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "RoFormerModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roformer", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roformer", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "rotary_value": false, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 50000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/182c68e879e874c90ea9eb0e8bdf6afe5a8b5dd19a4e8db31092a25b20a139eb/bc32d52c7cefd7453022.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/182c68e879e874c90ea9eb0e8bdf6afe5a8b5dd19a4e8db31092a25b20a139eb/bc32d52c7cefd7453022.json new file mode 100644 index 0000000000000000000000000000000000000000..9851a91f9d0df7c3493ab071db18aa7ca773bd09 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/182c68e879e874c90ea9eb0e8bdf6afe5a8b5dd19a4e8db31092a25b20a139eb/bc32d52c7cefd7453022.json @@ -0,0 +1,43 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DistilBertModel", + "_task": "fill-mask", + "activation": "gelu", + "architectures": [ + "DistilBertModel" + ], + "attention_dropout": 0.1, + "dim": 32, + "dropout": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dim": 37, + "initializer_range": 0.02, + "max_position_embeddings": 512, + "model_type": "distilbert", + "n_heads": 4, + "n_layers": 5, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "distilbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "qa_dropout": 0.1, + "seq_classif_dropout": 0.2, + "sinusoidal_pos_embds": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1854a13ac9082fe111f66db8335130f3b4b7f078b3a76726128e45f159f62fea/fdfa7e53709c9f8b70a0.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1854a13ac9082fe111f66db8335130f3b4b7f078b3a76726128e45f159f62fea/fdfa7e53709c9f8b70a0.json new file mode 100644 index 0000000000000000000000000000000000000000..0c8107bf798429c097f8c2a78e94def2f2b08601 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1854a13ac9082fe111f66db8335130f3b4b7f078b3a76726128e45f159f62fea/fdfa7e53709c9f8b70a0.json @@ -0,0 +1,98 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "flaubert/flaubert_small_cased", + "_task": "text-classification", + "amp": 1, + "architectures": [ + "FlaubertWithLMHeadModel" + ], + "asm": false, + "attention_dropout": 0.1, + "bos_index": 0, + "bptt": 512, + "causal": false, + "clip_grad_norm": 5, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 512, + "embed_init_std": 0.02209708691207961, + "encoder_only": true, + "end_n_top": 5, + "eos_index": 1, + "fp16": true, + "gelu_activation": true, + "group_by_size": true, + "id2lang": { + "0": "fr" + }, + "init_std": 0.02, + "is_encoder": true, + "lang2id": { + "fr": 0 + }, + "lang_id": 0, + "langs": [ + "fr" + ], + "layer_norm_eps": 1e-06, + "layerdrop": 0.2, + "lg_sampling_factor": -1, + "lgs": "fr", + "mask_index": 5, + "mask_token_id": 0, + "max_batch_size": 0, + "max_position_embeddings": 512, + "max_vocab": -1, + "mlm_steps": [ + [ + "fr", + null + ] + ], + "model_type": "flaubert", + "n_heads": 8, + "n_langs": 1, + "n_layers": 6, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "flaubert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "pad_index": 2, + "pre_norm": true, + "sample_alpha": 0, + "share_inout_emb": true, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "first", + "summary_use_proj": true, + "tokens_per_batch": -1, + "unk_index": 3, + "use_lang_emb": true, + "vocab_size": 68729, + "word_blank": 0, + "word_dropout": 0, + "word_keep": 0.1, + "word_mask": 0.8, + "word_mask_keep_rand": "0.8,0.1,0.1", + "word_pred": 0.15, + "word_rand": 0.1, + "word_shuffle": 0 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1b09d610295ddf619209eb3cbdfbb014ccd865caac8fa1d77bcde0a09744bc79/b74fb7c3d127d2361d6a.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1b09d610295ddf619209eb3cbdfbb014ccd865caac8fa1d77bcde0a09744bc79/b74fb7c3d127d2361d6a.json new file mode 100644 index 0000000000000000000000000000000000000000..cb9e911cb4e3dc2da5d66b430bfe9cd59a9d2df6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1b09d610295ddf619209eb3cbdfbb014ccd865caac8fa1d77bcde0a09744bc79/b74fb7c3d127d2361d6a.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "dtype": "bfloat16", + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "partial_rotary_factor": 1.0, + "rope_theta": 250000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1b24928d3034020367f17bdd4d37aeae11c152a99e5c0c13a48fbe3b048878bf/6be8e4dc53ea1d4c19c8.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1b24928d3034020367f17bdd4d37aeae11c152a99e5c0c13a48fbe3b048878bf/6be8e4dc53ea1d4c19c8.json new file mode 100644 index 0000000000000000000000000000000000000000..e8ebffe3aa80a001fb5f62237ead681f838ad80c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1b24928d3034020367f17bdd4d37aeae11c152a99e5c0c13a48fbe3b048878bf/6be8e4dc53ea1d4c19c8.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ElectraModel", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "ElectraModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "electra", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "electra", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "summary_activation": "gelu", + "summary_last_dropout": 0.1, + "summary_type": "first", + "summary_use_proj": true, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1b24928d3034020367f17bdd4d37aeae11c152a99e5c0c13a48fbe3b048878bf/fe23ab80b188555b4b3e.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1b24928d3034020367f17bdd4d37aeae11c152a99e5c0c13a48fbe3b048878bf/fe23ab80b188555b4b3e.json new file mode 100644 index 0000000000000000000000000000000000000000..6448540d123df3eb19308e47e146481a3b96db75 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1b24928d3034020367f17bdd4d37aeae11c152a99e5c0c13a48fbe3b048878bf/fe23ab80b188555b4b3e.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ElectraModel", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "ElectraModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "electra", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "electra", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "summary_activation": "gelu", + "summary_last_dropout": 0.1, + "summary_type": "first", + "summary_use_proj": true, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1bbb8a5abd82cf09875a766441ae5775140034acf37d7dbd1855ba733dde5c1a/13df271b67157400bb7d.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1bbb8a5abd82cf09875a766441ae5775140034acf37d7dbd1855ba733dde5c1a/13df271b67157400bb7d.json new file mode 100644 index 0000000000000000000000000000000000000000..84484addd42f16fd4371713057eb9bcc76500b00 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1bbb8a5abd82cf09875a766441ae5775140034acf37d7dbd1855ba733dde5c1a/13df271b67157400bb7d.json @@ -0,0 +1,225 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolVLM-256M-Instruct", + "_task": "image-text-to-text", + "architectures": [ + "Idefics3ForConditionalGeneration" + ], + "dtype": "bfloat16", + "image_token_id": 49190, + "model_type": "idefics3", + "neuron": { + "_serialized_key": "NxDVLMNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolVLM-256M-Instruct", + "checkpoint_revision": "7e3e67edbbed1bf9888184d9df282b700a323964", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "image_seq_len": 64, + "image_size": 512, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 2048, + "max_num_images": 17, + "max_topk": 256, + "n_active_tokens": 2048, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 1024, + "sequence_length": 2048, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "scale_factor": 4, + "text_config": { + "_attn_implementation_autoset": false, + "_flash_attn_2_enabled": true, + "_name_or_path": "None", + "add_cross_attention": false, + "architectures": [ + "VLlama3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 2, + "finetuning_task": null, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 576, + "initializer_range": 0.041666666666666664, + "intermediate_size": 1536, + "is_decoder": false, + "is_llama_config": true, + "max_position_embeddings": 8192, + "mlp_bias": false, + "model_type": "llama", + "neftune_noise_alpha": 0.0, + "num_attention_heads": 9, + "num_hidden_layers": 30, + "num_key_value_heads": 3, + "pad_token_id": 2, + "perceiver_config": { + "_attn_implementation_autoset": false, + "_name_or_path": "", + "add_cross_attention": false, + "architectures": null, + "attention_dropout": 0.0, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "chunk_size_feed_forward": 0, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "diversity_penalty": 0.0, + "do_sample": false, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": null, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "silu", + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "is_decoder": false, + "is_encoder_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "length_penalty": 1.0, + "max_length": 20, + "min_length": 0, + "model_type": "vllama3", + "no_repeat_ngram_size": 0, + "num_beam_groups": 1, + "num_beams": 1, + "num_key_value_heads": 1, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": null, + "prefix": null, + "problem_type": null, + "pruned_heads": {}, + "qk_layer_norms_perceiver": false, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "resampler_depth": 6, + "resampler_head_dim": 96, + "resampler_n_heads": 16, + "resampler_n_latents": 64, + "return_dict": true, + "return_dict_in_generate": false, + "sep_token_id": null, + "suppress_tokens": null, + "task_specific_params": null, + "temperature": 1.0, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": null, + "torchscript": false, + "transformers_version": "4.46.0", + "typical_p": 1.0, + "use_bfloat16": false + }, + "pixel_shuffle_factor": 4, + "prefix": null, + "pretraining_tp": 1, + "pruned_heads": {}, + "qk_layer_norms": false, + "rms_norm_eps": 1e-05, + "rope_interleaved": false, + "rope_parameters": { + "rope_theta": 100000, + "rope_type": "default" + }, + "sep_token_id": null, + "task_specific_params": null, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": false, + "tokenizer_class": null, + "torchscript": false, + "transformers.js_config": { + "kv_cache_dtype": { + "fp16": "float16", + "q4f16": "float16" + } + }, + "use_bfloat16": false, + "use_cache": true, + "use_resampler": false, + "vocab_size": 49280 + }, + "tie_word_embeddings": false, + "transformers.js_config": { + "kv_cache_dtype": { + "fp16": "float16", + "q4f16": "float16" + } + }, + "use_cache": true, + "vision_config": { + "_attn_implementation_autoset": false, + "add_cross_attention": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "eos_token_id": null, + "finetuning_task": null, + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 768, + "image_size": 512, + "initializer_range": 0.02, + "intermediate_size": 3072, + "is_decoder": false, + "layer_norm_eps": 1e-06, + "max_image_size": { + "longest_edge": 512 + }, + "model_type": "idefics3_vision", + "num_attention_heads": 12, + "num_channels": 3, + "num_hidden_layers": 12, + "pad_token_id": null, + "patch_size": 16, + "prefix": null, + "pruned_heads": {}, + "sep_token_id": null, + "size": { + "longest_edge": 2048 + }, + "task_specific_params": null, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": false, + "tokenizer_class": null, + "torchscript": false, + "use_base_siglip": true, + "use_bfloat16": false + }, + "vocab_size": 49280 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1bc1a717bdab964bdb3ee14014feb15640770139ce32fecc86a88fdbf9b0bfce/e9c92f51c5852325ab39.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1bc1a717bdab964bdb3ee14014feb15640770139ce32fecc86a88fdbf9b0bfce/e9c92f51c5852325ab39.json new file mode 100644 index 0000000000000000000000000000000000000000..3e49857eb477c074f052baf44949fa10e946ad5d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1bc1a717bdab964bdb3ee14014feb15640770139ce32fecc86a88fdbf9b0bfce/e9c92f51c5852325ab39.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-XLMModel", + "_task": "token-classification", + "architectures": [ + "XLMModel" + ], + "asm": false, + "attention_dropout": 0.1, + "bos_index": 0, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "eos_index": 1, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "mask_index": 5, + "mask_token_id": 5, + "max_position_embeddings": 512, + "model_type": "xlm", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "xlm", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "pad_index": 2, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": true, + "vocab_size": 30145 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1be1133ebfc208727fbf6793121d10fdc9eb6878b9ce71fea47004b03d0e6254/2731814c90335f8ff3cb.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1be1133ebfc208727fbf6793121d10fdc9eb6878b9ce71fea47004b03d0e6254/2731814c90335f8ff3cb.json new file mode 100644 index 0000000000000000000000000000000000000000..60b79754471c0c4b5a50e84eb0aa6ea396c5c5b5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1be1133ebfc208727fbf6793121d10fdc9eb6878b9ce71fea47004b03d0e6254/2731814c90335f8ff3cb.json @@ -0,0 +1,105 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-Wav2Vec2Model", + "_task": "automatic-speech-recognition", + "activation_dropout": 0.1, + "adapter_attn_dim": null, + "adapter_kernel_size": 3, + "adapter_stride": 2, + "add_adapter": false, + "apply_spec_augment": true, + "architectures": [ + "Wav2Vec2Model" + ], + "attention_dropout": 0.1, + "classifier_proj_size": 256, + "codevector_dim": 256, + "contrastive_logits_temperature": 0.1, + "conv_bias": false, + "conv_dim": [ + 32, + 32, + 32 + ], + "conv_kernel": [ + 8, + 8, + 8 + ], + "conv_stride": [ + 4, + 4, + 4 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "diversity_loss_weight": 0.1, + "do_stable_layer_norm": false, + "dtype": "float32", + "feat_extract_activation": "gelu", + "feat_extract_dropout": 0.0, + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_quantizer_dropout": 0.0, + "final_dropout": 0.1, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_dropout_prob": 0.1, + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 20, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 2, + "mask_time_min_masks": 2, + "mask_time_prob": 0.5, + "model_type": "wav2vec2", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "wav2vec2", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_audio_sequence_length": 100000, + "static_batch_size": 1, + "task": "automatic-speech-recognition", + "tensor_parallel_size": 1 + }, + "num_adapter_layers": 1, + "num_attention_heads": 2, + "num_codevector_groups": 2, + "num_codevectors_per_group": 320, + "num_conv_pos_embedding_groups": 2, + "num_conv_pos_embeddings": 16, + "num_feat_extract_layers": 3, + "num_hidden_layers": 4, + "num_negatives": 100, + "output_hidden_size": 16, + "proj_codevector_dim": 256, + "tdnn_dilation": [ + 1, + 2 + ], + "tdnn_dim": [ + 32, + 32 + ], + "tdnn_kernel": [ + 5, + 3 + ], + "use_weighted_layer_sum": false, + "vocab_size": 32, + "xvector_output_dim": 32 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1be1133ebfc208727fbf6793121d10fdc9eb6878b9ce71fea47004b03d0e6254/597d0cb71b0653906f72.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1be1133ebfc208727fbf6793121d10fdc9eb6878b9ce71fea47004b03d0e6254/597d0cb71b0653906f72.json new file mode 100644 index 0000000000000000000000000000000000000000..2accbf95a79e2f7d847f6370fdc466d0da335263 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1be1133ebfc208727fbf6793121d10fdc9eb6878b9ce71fea47004b03d0e6254/597d0cb71b0653906f72.json @@ -0,0 +1,105 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-Wav2Vec2Model", + "_task": "automatic-speech-recognition", + "activation_dropout": 0.1, + "adapter_attn_dim": null, + "adapter_kernel_size": 3, + "adapter_stride": 2, + "add_adapter": false, + "apply_spec_augment": true, + "architectures": [ + "Wav2Vec2Model" + ], + "attention_dropout": 0.1, + "classifier_proj_size": 256, + "codevector_dim": 256, + "contrastive_logits_temperature": 0.1, + "conv_bias": false, + "conv_dim": [ + 32, + 32, + 32 + ], + "conv_kernel": [ + 8, + 8, + 8 + ], + "conv_stride": [ + 4, + 4, + 4 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "diversity_loss_weight": 0.1, + "do_stable_layer_norm": false, + "dtype": "float32", + "feat_extract_activation": "gelu", + "feat_extract_dropout": 0.0, + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_quantizer_dropout": 0.0, + "final_dropout": 0.1, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_dropout_prob": 0.1, + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 20, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 2, + "mask_time_min_masks": 2, + "mask_time_prob": 0.5, + "model_type": "wav2vec2", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "wav2vec2", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_audio_sequence_length": 100000, + "static_batch_size": 1, + "task": "automatic-speech-recognition", + "tensor_parallel_size": 1 + }, + "num_adapter_layers": 1, + "num_attention_heads": 2, + "num_codevector_groups": 2, + "num_codevectors_per_group": 320, + "num_conv_pos_embedding_groups": 2, + "num_conv_pos_embeddings": 16, + "num_feat_extract_layers": 3, + "num_hidden_layers": 4, + "num_negatives": 100, + "output_hidden_size": 16, + "proj_codevector_dim": 256, + "tdnn_dilation": [ + 1, + 2 + ], + "tdnn_dim": [ + 32, + 32 + ], + "tdnn_kernel": [ + 5, + 3 + ], + "use_weighted_layer_sum": false, + "vocab_size": 32, + "xvector_output_dim": 32 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1dc5c929d58fc9865ec52d89c15b3a5c0adff91cb7a2e1b2520bc158f9660640/31284efe689d8718ec0b.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1dc5c929d58fc9865ec52d89c15b3a5c0adff91cb7a2e1b2520bc158f9660640/31284efe689d8718ec0b.json new file mode 100644 index 0000000000000000000000000000000000000000..d32c40307d92b0b7b66bb8358b49361531bd8d5c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1dc5c929d58fc9865ec52d89c15b3a5c0adff91cb7a2e1b2520bc158f9660640/31284efe689d8718ec0b.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MobileBertModel", + "_task": "text-classification", + "architectures": [ + "MobileBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_activation": true, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 37, + "intra_bottleneck_size": 128, + "key_query_shared_bottleneck": true, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mobilebert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mobilebert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "normalization_type": "no_norm", + "num_attention_heads": 4, + "num_feedforward_networks": 4, + "num_hidden_layers": 5, + "tie_word_embeddings": true, + "trigram_input": true, + "true_hidden_size": 128, + "type_vocab_size": 16, + "use_bottleneck": true, + "use_bottleneck_attention": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1e61ad9a032957f61542c2c62d18b7e08b4b99e86eaa92d46d294a7911d8c4ba/253af4a9a064191237a9.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1e61ad9a032957f61542c2c62d18b7e08b4b99e86eaa92d46d294a7911d8c4ba/253af4a9a064191237a9.json new file mode 100644 index 0000000000000000000000000000000000000000..d53b8b62ace1b4f1f5c78cc42324fcf6aeb91d9b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/1e61ad9a032957f61542c2c62d18b7e08b4b99e86eaa92d46d294a7911d8c4ba/253af4a9a064191237a9.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RobertaModel", + "_task": "token-classification", + "architectures": [ + "RobertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1024 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/2370ccabfe2620526012efed7890227b8c8cd1f40b71c04ddbf000d35f7c3f49/8143a57937ff881dc97f.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/2370ccabfe2620526012efed7890227b8c8cd1f40b71c04ddbf000d35f7c3f49/8143a57937ff881dc97f.json new file mode 100644 index 0000000000000000000000000000000000000000..f18aa0d72c50aa001a862c4ccae1ab2cfd43640d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/2370ccabfe2620526012efed7890227b8c8cd1f40b71c04ddbf000d35f7c3f49/8143a57937ff881dc97f.json @@ -0,0 +1,61 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-XLMModel", + "_task": "text-classification", + "architectures": [ + "XLMModel" + ], + "asm": false, + "attention_dropout": 0.1, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "mask_index": 5, + "mask_token_id": 5, + "max_position_embeddings": 512, + "model_type": "xlm", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "xlm", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "tie_word_embeddings": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": true, + "vocab_size": 30145 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/241a0b43ea5763ed688059df76dd7489e03f4931042b930a12a6951825d38826/1adc0dc5bc677d69f186.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/241a0b43ea5763ed688059df76dd7489e03f4931042b930a12a6951825d38826/1adc0dc5bc677d69f186.json new file mode 100644 index 0000000000000000000000000000000000000000..037d770c772f1c81f8992aa88a69ad65e85657f6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/241a0b43ea5763ed688059df76dd7489e03f4931042b930a12a6951825d38826/1adc0dc5bc677d69f186.json @@ -0,0 +1,49 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ConvBertModel", + "_task": "fill-mask", + "add_cross_attention": false, + "architectures": [ + "ConvBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "conv_kernel_size": 9, + "dtype": "float32", + "embedding_size": 768, + "head_ratio": 2, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "convbert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "convbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_groups": 1, + "num_hidden_layers": 5, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/241a0b43ea5763ed688059df76dd7489e03f4931042b930a12a6951825d38826/ab60038681ce5d9f54ba.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/241a0b43ea5763ed688059df76dd7489e03f4931042b930a12a6951825d38826/ab60038681ce5d9f54ba.json new file mode 100644 index 0000000000000000000000000000000000000000..e36e727833bb31ec8c940d4f6b3a6b63e2f775a2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/241a0b43ea5763ed688059df76dd7489e03f4931042b930a12a6951825d38826/ab60038681ce5d9f54ba.json @@ -0,0 +1,49 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ConvBertModel", + "_task": "fill-mask", + "add_cross_attention": false, + "architectures": [ + "ConvBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "conv_kernel_size": 9, + "dtype": "float32", + "embedding_size": 768, + "head_ratio": 2, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "convbert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "convbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_groups": 1, + "num_hidden_layers": 5, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/25f7ff82d31412fc390d8440d8a52bd105c10a2bc31a312f2dd0e1c3a4fb0362/4bae5d94fb5d198514d4.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/25f7ff82d31412fc390d8440d8a52bd105c10a2bc31a312f2dd0e1c3a4fb0362/4bae5d94fb5d198514d4.json new file mode 100644 index 0000000000000000000000000000000000000000..c8bef9d8fbacfc8112599db91924539ff1a21763 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/25f7ff82d31412fc390d8440d8a52bd105c10a2bc31a312f2dd0e1c3a4fb0362/4bae5d94fb5d198514d4.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RobertaModel", + "_task": "question-answering", + "add_cross_attention": false, + "architectures": [ + "RobertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1024 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/2619ed9b64c901f1a211aa80eef9a9d7729cb55d3737aee5faf16f583a23dc39/d2923fbdd1af5df4cee7.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/2619ed9b64c901f1a211aa80eef9a9d7729cb55d3737aee5faf16f583a23dc39/d2923fbdd1af5df4cee7.json new file mode 100644 index 0000000000000000000000000000000000000000..cf8dc1c18157ba3a744c6c4a2002a8f0637bb050 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/2619ed9b64c901f1a211aa80eef9a9d7729cb55d3737aee5faf16f583a23dc39/d2923fbdd1af5df4cee7.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MobileBertModel", + "_task": "token-classification", + "architectures": [ + "MobileBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_activation": true, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 37, + "intra_bottleneck_size": 128, + "key_query_shared_bottleneck": true, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mobilebert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mobilebert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "normalization_type": "no_norm", + "num_attention_heads": 4, + "num_feedforward_networks": 4, + "num_hidden_layers": 5, + "trigram_input": true, + "true_hidden_size": 128, + "type_vocab_size": 16, + "use_bottleneck": true, + "use_bottleneck_attention": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/26ac4ae14271f4fa862b528400ea3d649dadfefeb13827408f81128a3f42d090/8f8c61082e8765f7bd9e.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/26ac4ae14271f4fa862b528400ea3d649dadfefeb13827408f81128a3f42d090/8f8c61082e8765f7bd9e.json new file mode 100644 index 0000000000000000000000000000000000000000..a8ea7d698f82be0a7d0c052d12937ad05fd6630d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/26ac4ae14271f4fa862b528400ea3d649dadfefeb13827408f81128a3f42d090/8f8c61082e8765f7bd9e.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "fill-mask", + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/286fbf5b9ab1424f28709db3053ef41433e870dcb77d59a0b8bf7b9d57ad4073/67fc5ccb1bb8673a56b2.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/286fbf5b9ab1424f28709db3053ef41433e870dcb77d59a0b8bf7b9d57ad4073/67fc5ccb1bb8673a56b2.json new file mode 100644 index 0000000000000000000000000000000000000000..398c6c497e842a104385628d9196cca8d1a102c2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/286fbf5b9ab1424f28709db3053ef41433e870dcb77d59a0b8bf7b9d57ad4073/67fc5ccb1bb8673a56b2.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "token-classification", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/28c5da586351a5eae4210bba22c8365cdff60b08d68690c167ada99e6b873d11/6c1c772c043f7d08349c.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/28c5da586351a5eae4210bba22c8365cdff60b08d68690c167ada99e6b873d11/6c1c772c043f7d08349c.json new file mode 100644 index 0000000000000000000000000000000000000000..f26ba47539a5849531db55d584c993e82538c5f2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/28c5da586351a5eae4210bba22c8365cdff60b08d68690c167ada99e6b873d11/6c1c772c043f7d08349c.json @@ -0,0 +1,49 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ConvBertModel", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "ConvBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "conv_kernel_size": 9, + "dtype": "float32", + "embedding_size": 768, + "head_ratio": 2, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "convbert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "convbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_groups": 1, + "num_hidden_layers": 5, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/2a52eb18c43c21586782604b014d37dfad416b8deb1e8b5e0a55a6978e9fda6e/5fd8bfef594f4d504d19.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/2a52eb18c43c21586782604b014d37dfad416b8deb1e8b5e0a55a6978e9fda6e/5fd8bfef594f4d504d19.json new file mode 100644 index 0000000000000000000000000000000000000000..63008ca4626c3ff3de6c886cc911a2ce5cd91bb9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/2a52eb18c43c21586782604b014d37dfad416b8deb1e8b5e0a55a6978e9fda6e/5fd8bfef594f4d504d19.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ElectraModel", + "_task": "token-classification", + "add_cross_attention": false, + "architectures": [ + "ElectraModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "electra", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "electra", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "summary_activation": "gelu", + "summary_last_dropout": 0.1, + "summary_type": "first", + "summary_use_proj": true, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/2aae59e740ef2d96820e013102d47e52925556644966a2c36d62db358bc3fd61/8fd07da0df2a2f31aff8.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/2aae59e740ef2d96820e013102d47e52925556644966a2c36d62db358bc3fd61/8fd07da0df2a2f31aff8.json new file mode 100644 index 0000000000000000000000000000000000000000..fbcae5e06f1a1b3b813a15cf8d66832021086c0a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/2aae59e740ef2d96820e013102d47e52925556644966a2c36d62db358bc3fd61/8fd07da0df2a2f31aff8.json @@ -0,0 +1,107 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "tengomucho/tiny-random-gemma-3-vlm", + "_task": "image-text-to-text", + "architectures": [ + "Gemma3ForConditionalGeneration" + ], + "boi_token_index": 255999, + "dtype": "bfloat16", + "eoi_token_index": 256000, + "image_token_index": 262144, + "initializer_range": 0.02, + "mm_tokens_per_image": 256, + "model_type": "gemma3", + "neuron": { + "_serialized_key": "NxDVLMNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "tengomucho/tiny-random-gemma-3-vlm", + "checkpoint_revision": "880db0f4a0e1000cec5193ea9a93c30ce425c0e5", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "image_seq_len": 256, + "image_size": 896, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 2048, + "max_num_images": 5, + "max_topk": 256, + "n_active_tokens": 2048, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 2048, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_key_value_heads": 2, + "text_config": { + "_sliding_window_pattern": 2, + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "dtype": "bfloat16", + "eos_token_id": 1, + "final_logit_softcapping": null, + "head_dim": 64, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 128, + "initializer_range": 0.02, + "intermediate_size": 256, + "layer_types": [ + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "model_type": "gemma3_text", + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "pad_token_id": 0, + "query_pre_attn_scalar": 168, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "full_attention": { + "factor": 8.0, + "rope_theta": 1000000.0, + "rope_type": "linear" + }, + "sliding_attention": { + "rope_theta": 10000.0, + "rope_type": "default" + } + }, + "sliding_window": 1024, + "sliding_window_pattern": 2, + "tie_word_embeddings": true, + "use_bidirectional_attention": false, + "use_cache": true, + "vocab_size": 262208 + }, + "tie_word_embeddings": true, + "vision_config": { + "attention_dropout": 0.0, + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 32, + "image_size": 896, + "intermediate_size": 128, + "layer_norm_eps": 1e-06, + "model_type": "siglip_vision_model", + "num_attention_heads": 2, + "num_channels": 3, + "num_hidden_layers": 2, + "patch_size": 14, + "vision_use_head": false + } +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/2f125e7061acee698b5af63805f945ab70e39c76f290e65f8a8d57c3c917bfc8/e8a1f65ccdc1baf074dd.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/2f125e7061acee698b5af63805f945ab70e39c76f290e65f8a8d57c3c917bfc8/e8a1f65ccdc1baf074dd.json new file mode 100644 index 0000000000000000000000000000000000000000..5c00fc09b744cc23d5012fe515dd2dddded8fcd9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/2f125e7061acee698b5af63805f945ab70e39c76f290e65f8a8d57c3c917bfc8/e8a1f65ccdc1baf074dd.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RoFormerModel", + "_task": "feature-extraction", + "architectures": [ + "RoFormerModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roformer", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roformer", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "rotary_value": false, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 50000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/2f1eed3dd511485fdb516d19469fd212dcad16b3d67167cfcdccdc2324d13678/4cf01c220325f9c0461a.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/2f1eed3dd511485fdb516d19469fd212dcad16b3d67167cfcdccdc2324d13678/4cf01c220325f9c0461a.json new file mode 100644 index 0000000000000000000000000000000000000000..08639645a6779288d5429b9c589a19d227e70004 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/2f1eed3dd511485fdb516d19469fd212dcad16b3d67167cfcdccdc2324d13678/4cf01c220325f9c0461a.json @@ -0,0 +1,125 @@ +{ + "_entry_class": "MultiModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-stable-diffusion-torch", + "_task": null, + "text_encoder": { + "architectures": [ + "CLIPTextModel" + ], + "attention_dropout": 0.0, + "dropout": 0.0, + "dtype": "float32", + "export_model_type": "clip-text-model", + "hidden_act": "quick_gelu", + "hidden_size": 32, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 77, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "vocab_size": 1000 + }, + "unet": { + "_class_name": "UNet2DConditionModel", + "act_fn": "silu", + "addition_embed_type": null, + "addition_embed_type_num_heads": 64, + "addition_time_embed_dim": null, + "attention_head_dim": 8, + "attention_type": "default", + "block_out_channels": [ + 32, + 64 + ], + "center_input_sample": false, + "class_embed_type": null, + "class_embeddings_concat": false, + "conv_in_kernel": 3, + "conv_out_kernel": 3, + "cross_attention_dim": 32, + "cross_attention_norm": null, + "down_block_types": [ + "DownBlock2D", + "CrossAttnDownBlock2D" + ], + "downsample_padding": 1, + "dropout": 0.0, + "dual_cross_attention": false, + "encoder_hid_dim": null, + "encoder_hid_dim_type": null, + "flip_sin_to_cos": true, + "freq_shift": 0, + "in_channels": 4, + "layers_per_block": 2, + "mid_block_only_cross_attention": null, + "mid_block_scale_factor": 1, + "mid_block_type": "UNetMidBlock2DCrossAttn", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 32, + "static_num_channels": 4, + "static_sequence_length": 77, + "static_vae_scale_factor": 2, + "static_width": 32, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_eps": 1e-05, + "norm_num_groups": 32, + "num_attention_heads": null, + "num_class_embeds": null, + "only_cross_attention": false, + "out_channels": 4, + "output_attentions": false, + "projection_class_embeddings_input_dim": null, + "resnet_out_scale_factor": 1.0, + "resnet_skip_time_act": false, + "resnet_time_scale_shift": "default", + "reverse_transformer_layers_per_block": null, + "time_cond_proj_dim": null, + "time_embedding_act_fn": null, + "time_embedding_dim": null, + "time_embedding_type": "positional", + "timestep_post_act": null, + "transformer_layers_per_block": 1, + "up_block_types": [ + "CrossAttnUpBlock2D", + "UpBlock2D" + ], + "upcast_attention": false, + "use_linear_projection": false + } +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/350126c8de0736b390b4701f10d36ff5c9781438073191125401e9d9fc49d4ab/ba4887019f49aa2a8409.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/350126c8de0736b390b4701f10d36ff5c9781438073191125401e9d9fc49d4ab/ba4887019f49aa2a8409.json new file mode 100644 index 0000000000000000000000000000000000000000..1125bf98ee3de88d718f209817c2cd333f55fe8a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/350126c8de0736b390b4701f10d36ff5c9781438073191125401e9d9fc49d4ab/ba4887019f49aa2a8409.json @@ -0,0 +1,49 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ConvBertModel", + "_task": "question-answering", + "add_cross_attention": false, + "architectures": [ + "ConvBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "conv_kernel_size": 9, + "dtype": "float32", + "embedding_size": 768, + "head_ratio": 2, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "convbert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "convbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_groups": 1, + "num_hidden_layers": 5, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/35d9ffee821c888d31825e0f1426a12375c7718ef0ebb8644d758d8d525f5018/976fd25422fa2139eafa.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/35d9ffee821c888d31825e0f1426a12375c7718ef0ebb8644d758d8d525f5018/976fd25422fa2139eafa.json new file mode 100644 index 0000000000000000000000000000000000000000..4b1e411deb8a99112a5a6c7cc93529186af8da9d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/35d9ffee821c888d31825e0f1426a12375c7718ef0ebb8644d758d8d525f5018/976fd25422fa2139eafa.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RoFormerModel", + "_task": "fill-mask", + "architectures": [ + "RoFormerModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roformer", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roformer", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "rotary_value": false, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 50000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3688576a9fb396c9f6bd9fc1ecd2b945081cfc13f3b4431e431d32832476937d/24f76ca387ef92cd6ae1.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3688576a9fb396c9f6bd9fc1ecd2b945081cfc13f3b4431e431d32832476937d/24f76ca387ef92cd6ae1.json new file mode 100644 index 0000000000000000000000000000000000000000..724f8e9c8a41fcd10c4092a35e13358a6c80487a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3688576a9fb396c9f6bd9fc1ecd2b945081cfc13f3b4431e431d32832476937d/24f76ca387ef92cd6ae1.json @@ -0,0 +1,42 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MPNetModel", + "_task": "fill-mask", + "architectures": [ + "MPNetModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 64, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mpnet", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mpnet", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "relative_attention_num_buckets": 32, + "tie_word_embeddings": true, + "vocab_size": 1125 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/379d25f01d4ea8fcdeece17dfa261e97ab50dffda55c0f4c40e02dbc13792e3d/5a88e44af18d4ac457a3.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/379d25f01d4ea8fcdeece17dfa261e97ab50dffda55c0f4c40e02dbc13792e3d/5a88e44af18d4ac457a3.json new file mode 100644 index 0000000000000000000000000000000000000000..a3247b01ed9856742934a3511915d86a42c7f21e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/379d25f01d4ea8fcdeece17dfa261e97ab50dffda55c0f4c40e02dbc13792e3d/5a88e44af18d4ac457a3.json @@ -0,0 +1,42 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MPNetModel", + "_task": "token-classification", + "architectures": [ + "MPNetModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 64, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mpnet", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mpnet", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "relative_attention_num_buckets": 32, + "tie_word_embeddings": true, + "vocab_size": 1125 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3a8bd6e0c7c78b1525323d84e31dbc8eb2b537a88f6b56a8bd3f774dc1f5d070/2fa51921cfc043b5c94e.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3a8bd6e0c7c78b1525323d84e31dbc8eb2b537a88f6b56a8bd3f774dc1f5d070/2fa51921cfc043b5c94e.json new file mode 100644 index 0000000000000000000000000000000000000000..ea6cc5648950a72460805ab1436cc1431d18ac58 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3a8bd6e0c7c78b1525323d84e31dbc8eb2b537a88f6b56a8bd3f774dc1f5d070/2fa51921cfc043b5c94e.json @@ -0,0 +1,48 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-camembert", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "CamembertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "camembert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "camembert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3a8bd6e0c7c78b1525323d84e31dbc8eb2b537a88f6b56a8bd3f774dc1f5d070/7c2cd95251fb5f02a712.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3a8bd6e0c7c78b1525323d84e31dbc8eb2b537a88f6b56a8bd3f774dc1f5d070/7c2cd95251fb5f02a712.json new file mode 100644 index 0000000000000000000000000000000000000000..32b1783fe511c240d913fef2117f461d24dc5733 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3a8bd6e0c7c78b1525323d84e31dbc8eb2b537a88f6b56a8bd3f774dc1f5d070/7c2cd95251fb5f02a712.json @@ -0,0 +1,48 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-camembert", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "CamembertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "camembert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "camembert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3ab92a25746cedc1bdb4831fd19b883654dc738f5b9ee8307bff0feeac7299db/25c0d4759e1c65f1434e.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3ab92a25746cedc1bdb4831fd19b883654dc738f5b9ee8307bff0feeac7299db/25c0d4759e1c65f1434e.json new file mode 100644 index 0000000000000000000000000000000000000000..20e985bd5ee6af1328eb6135e7be789956959a6e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3ab92a25746cedc1bdb4831fd19b883654dc738f5b9ee8307bff0feeac7299db/25c0d4759e1c65f1434e.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "token-classification", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3ab92a25746cedc1bdb4831fd19b883654dc738f5b9ee8307bff0feeac7299db/6295d3ca344af2b014db.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3ab92a25746cedc1bdb4831fd19b883654dc738f5b9ee8307bff0feeac7299db/6295d3ca344af2b014db.json new file mode 100644 index 0000000000000000000000000000000000000000..6ec30ed7d2303d4a1afd6e06123c59e522d7a546 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3ab92a25746cedc1bdb4831fd19b883654dc738f5b9ee8307bff0feeac7299db/6295d3ca344af2b014db.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "token-classification", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3ab92a25746cedc1bdb4831fd19b883654dc738f5b9ee8307bff0feeac7299db/6a1bd372d9f92f210f43.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3ab92a25746cedc1bdb4831fd19b883654dc738f5b9ee8307bff0feeac7299db/6a1bd372d9f92f210f43.json new file mode 100644 index 0000000000000000000000000000000000000000..d3aa6ce1bb7aa3c294f5f0046035a0a1197f9ef0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3ab92a25746cedc1bdb4831fd19b883654dc738f5b9ee8307bff0feeac7299db/6a1bd372d9f92f210f43.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "token-classification", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3cc8591ca884b0cdd9210cd639305bbcf75c716a5124e0c97fbcd4e0634ac106/86f60199412e20e389d5.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3cc8591ca884b0cdd9210cd639305bbcf75c716a5124e0c97fbcd4e0634ac106/86f60199412e20e389d5.json new file mode 100644 index 0000000000000000000000000000000000000000..f0ecdb0c6cbf6160b7f94e0f5675007b3bb942d4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3cc8591ca884b0cdd9210cd639305bbcf75c716a5124e0c97fbcd4e0634ac106/86f60199412e20e389d5.json @@ -0,0 +1,41 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MPNetModel", + "_task": "text-classification", + "architectures": [ + "MPNetModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 64, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mpnet", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mpnet", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "relative_attention_num_buckets": 32, + "vocab_size": 1125 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3f06e52fa4ba23717b7e919e2d06879055f296df484d57a4e58c3272e9ed1b20/13de9a99b66c407be8e9.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3f06e52fa4ba23717b7e919e2d06879055f296df484d57a4e58c3272e9ed1b20/13de9a99b66c407be8e9.json new file mode 100644 index 0000000000000000000000000000000000000000..5436f7dfa3866ada4000c8660fb4bb0e48373c79 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3f06e52fa4ba23717b7e919e2d06879055f296df484d57a4e58c3272e9ed1b20/13de9a99b66c407be8e9.json @@ -0,0 +1,45 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-camembert", + "_task": "feature-extraction", + "architectures": [ + "CamembertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "camembert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "camembert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3f302d3506bc13bbc72f7d5d273e6d4c93e311a2d5305600e88e0e50083f000c/3513078fbdd62768acba.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3f302d3506bc13bbc72f7d5d273e6d4c93e311a2d5305600e88e0e50083f000c/3513078fbdd62768acba.json new file mode 100644 index 0000000000000000000000000000000000000000..3af18be742447ece4025d6f2fca1c8996d0ff2be --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3f302d3506bc13bbc72f7d5d273e6d4c93e311a2d5305600e88e0e50083f000c/3513078fbdd62768acba.json @@ -0,0 +1,105 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-Wav2Vec2Model", + "_task": "audio-classification", + "activation_dropout": 0.1, + "adapter_attn_dim": null, + "adapter_kernel_size": 3, + "adapter_stride": 2, + "add_adapter": false, + "apply_spec_augment": true, + "architectures": [ + "Wav2Vec2Model" + ], + "attention_dropout": 0.1, + "classifier_proj_size": 256, + "codevector_dim": 256, + "contrastive_logits_temperature": 0.1, + "conv_bias": false, + "conv_dim": [ + 32, + 32, + 32 + ], + "conv_kernel": [ + 8, + 8, + 8 + ], + "conv_stride": [ + 4, + 4, + 4 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "diversity_loss_weight": 0.1, + "do_stable_layer_norm": false, + "dtype": "float32", + "feat_extract_activation": "gelu", + "feat_extract_dropout": 0.0, + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_quantizer_dropout": 0.0, + "final_dropout": 0.1, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_dropout_prob": 0.1, + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 20, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 2, + "mask_time_min_masks": 2, + "mask_time_prob": 0.5, + "model_type": "wav2vec2", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "wav2vec2", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_audio_sequence_length": 100000, + "static_batch_size": 1, + "task": "audio-classification", + "tensor_parallel_size": 1 + }, + "num_adapter_layers": 1, + "num_attention_heads": 2, + "num_codevector_groups": 2, + "num_codevectors_per_group": 320, + "num_conv_pos_embedding_groups": 2, + "num_conv_pos_embeddings": 16, + "num_feat_extract_layers": 3, + "num_hidden_layers": 4, + "num_negatives": 100, + "output_hidden_size": 16, + "proj_codevector_dim": 256, + "tdnn_dilation": [ + 1, + 2 + ], + "tdnn_dim": [ + 32, + 32 + ], + "tdnn_kernel": [ + 5, + 3 + ], + "use_weighted_layer_sum": false, + "vocab_size": 32, + "xvector_output_dim": 32 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3f302d3506bc13bbc72f7d5d273e6d4c93e311a2d5305600e88e0e50083f000c/f37a40d5fb9e1951bda4.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3f302d3506bc13bbc72f7d5d273e6d4c93e311a2d5305600e88e0e50083f000c/f37a40d5fb9e1951bda4.json new file mode 100644 index 0000000000000000000000000000000000000000..9c0ff98f38b6321498f46db2d91d54d7ba5ab2ba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/3f302d3506bc13bbc72f7d5d273e6d4c93e311a2d5305600e88e0e50083f000c/f37a40d5fb9e1951bda4.json @@ -0,0 +1,105 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-Wav2Vec2Model", + "_task": "audio-classification", + "activation_dropout": 0.1, + "adapter_attn_dim": null, + "adapter_kernel_size": 3, + "adapter_stride": 2, + "add_adapter": false, + "apply_spec_augment": true, + "architectures": [ + "Wav2Vec2Model" + ], + "attention_dropout": 0.1, + "classifier_proj_size": 256, + "codevector_dim": 256, + "contrastive_logits_temperature": 0.1, + "conv_bias": false, + "conv_dim": [ + 32, + 32, + 32 + ], + "conv_kernel": [ + 8, + 8, + 8 + ], + "conv_stride": [ + 4, + 4, + 4 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "diversity_loss_weight": 0.1, + "do_stable_layer_norm": false, + "dtype": "float32", + "feat_extract_activation": "gelu", + "feat_extract_dropout": 0.0, + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_quantizer_dropout": 0.0, + "final_dropout": 0.1, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_dropout_prob": 0.1, + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 20, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 2, + "mask_time_min_masks": 2, + "mask_time_prob": 0.5, + "model_type": "wav2vec2", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "wav2vec2", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_audio_sequence_length": 100000, + "static_batch_size": 1, + "task": "audio-classification", + "tensor_parallel_size": 1 + }, + "num_adapter_layers": 1, + "num_attention_heads": 2, + "num_codevector_groups": 2, + "num_codevectors_per_group": 320, + "num_conv_pos_embedding_groups": 2, + "num_conv_pos_embeddings": 16, + "num_feat_extract_layers": 3, + "num_hidden_layers": 4, + "num_negatives": 100, + "output_hidden_size": 16, + "proj_codevector_dim": 256, + "tdnn_dilation": [ + 1, + 2 + ], + "tdnn_dim": [ + 32, + 32 + ], + "tdnn_kernel": [ + 5, + 3 + ], + "use_weighted_layer_sum": false, + "vocab_size": 32, + "xvector_output_dim": 32 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/425e081e7120a0d7a46d42c5d4b4521a3cc24ae25460f2ae55eea2e0a17a43ad/964d3a1846fe146a1f18.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/425e081e7120a0d7a46d42c5d4b4521a3cc24ae25460f2ae55eea2e0a17a43ad/964d3a1846fe146a1f18.json new file mode 100644 index 0000000000000000000000000000000000000000..7efb7979e627726375f24599c1c6a467b9a690fa --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/425e081e7120a0d7a46d42c5d4b4521a3cc24ae25460f2ae55eea2e0a17a43ad/964d3a1846fe146a1f18.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ElectraModel", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "ElectraModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "electra", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "electra", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "summary_activation": "gelu", + "summary_last_dropout": 0.1, + "summary_type": "first", + "summary_use_proj": true, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/4261491457708e7e1afe2be4b3f2ab8357131f642a4bcc214b721a50d46f0336/699e290656265c6d3d7d.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/4261491457708e7e1afe2be4b3f2ab8357131f642a4bcc214b721a50d46f0336/699e290656265c6d3d7d.json new file mode 100644 index 0000000000000000000000000000000000000000..8c5865e7549dc624584b9b918ee920cd9781c7ef --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/4261491457708e7e1afe2be4b3f2ab8357131f642a4bcc214b721a50d46f0336/699e290656265c6d3d7d.json @@ -0,0 +1,49 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ElectraModel", + "_task": "feature-extraction", + "architectures": [ + "ElectraModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "electra", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "electra", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "summary_activation": "gelu", + "summary_last_dropout": 0.1, + "summary_type": "first", + "summary_use_proj": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/44f78eea2bad4f539500a8b8ae30201e1e2f3b3fee350c470f71c5043b306806/c56b2ada375a7823dfcc.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/44f78eea2bad4f539500a8b8ae30201e1e2f3b3fee350c470f71c5043b306806/c56b2ada375a7823dfcc.json new file mode 100644 index 0000000000000000000000000000000000000000..a6558eb82a22bcc074a59cd8a37d0ea92ec2f705 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/44f78eea2bad4f539500a8b8ae30201e1e2f3b3fee350c470f71c5043b306806/c56b2ada375a7823dfcc.json @@ -0,0 +1,56 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-xlm-roberta", + "_task": "question-answering", + "add_cross_attention": false, + "architectures": [ + "XLMRobertaForCausalLM" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "d_ff": 256, + "d_kv": 8, + "d_model": 64, + "dtype": "float32", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 256, + "initializer_range": 0.02, + "intermediate_size": 256, + "is_decoder": false, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 64, + "model_type": "xlm-roberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "xlm-roberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 2, + "num_decoder_layers": 2, + "num_heads": 2, + "num_hidden_layers": 2, + "num_layers": 2, + "output_past": true, + "position_embedding_type": "absolute", + "relative_attention_num_buckets": 32, + "tie_word_embeddings": true, + "type_vocab_size": 1, + "use_cache": true, + "vocab_size": 5002 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/46e68250601d6220ea02c6b2321aa325b2a3b5d0dc3a191c316cc1f70df44ca0/4b905909eeb379b47401.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/46e68250601d6220ea02c6b2321aa325b2a3b5d0dc3a191c316cc1f70df44ca0/4b905909eeb379b47401.json new file mode 100644 index 0000000000000000000000000000000000000000..5ea10d121f7a70f400d24e25b6829ac53654c6da --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/46e68250601d6220ea02c6b2321aa325b2a3b5d0dc3a191c316cc1f70df44ca0/4b905909eeb379b47401.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-XLMModel", + "_task": "question-answering", + "architectures": [ + "XLMModel" + ], + "asm": false, + "attention_dropout": 0.1, + "bos_index": 0, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "eos_index": 1, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "mask_index": 5, + "mask_token_id": 5, + "max_position_embeddings": 512, + "model_type": "xlm", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "xlm", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "pad_index": 2, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": true, + "vocab_size": 30145 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/47b7f5e359be6c5e3797429ad22e094f396b87d8fdfc9de35d9e2c294532777f/2ae990ff88d8ecdc7012.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/47b7f5e359be6c5e3797429ad22e094f396b87d8fdfc9de35d9e2c294532777f/2ae990ff88d8ecdc7012.json new file mode 100644 index 0000000000000000000000000000000000000000..c4d7c58a4b6fcc439f057e8c3d487f0c9d63e4e3 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/47b7f5e359be6c5e3797429ad22e094f396b87d8fdfc9de35d9e2c294532777f/2ae990ff88d8ecdc7012.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "fill-mask", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/47b7f5e359be6c5e3797429ad22e094f396b87d8fdfc9de35d9e2c294532777f/5b6e1a3c2703a37838bb.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/47b7f5e359be6c5e3797429ad22e094f396b87d8fdfc9de35d9e2c294532777f/5b6e1a3c2703a37838bb.json new file mode 100644 index 0000000000000000000000000000000000000000..d14f4d0b3f585e9413aa7ccc895cd411191021e9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/47b7f5e359be6c5e3797429ad22e094f396b87d8fdfc9de35d9e2c294532777f/5b6e1a3c2703a37838bb.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "fill-mask", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/4faed4399e1483ab41286569e0b24e968b23c68e1908556400279c6c1cd3f106/3bceb7d639ac50f4e447.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/4faed4399e1483ab41286569e0b24e968b23c68e1908556400279c6c1cd3f106/3bceb7d639ac50f4e447.json new file mode 100644 index 0000000000000000000000000000000000000000..da8341207ec39896026ff6a59833a7f5e893b26c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/4faed4399e1483ab41286569e0b24e968b23c68e1908556400279c6c1cd3f106/3bceb7d639ac50f4e447.json @@ -0,0 +1,45 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-camembert", + "_task": "question-answering", + "architectures": [ + "CamembertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "camembert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "camembert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/50a358e5ea05fe476aea209cc99757a448a47d0b82b96521eb2d713be2421176/9465f6995793f958dfe2.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/50a358e5ea05fe476aea209cc99757a448a47d0b82b96521eb2d713be2421176/9465f6995793f958dfe2.json new file mode 100644 index 0000000000000000000000000000000000000000..3ddebdec34f00d7bc30ab1ea45e9358440a513e5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/50a358e5ea05fe476aea209cc99757a448a47d0b82b96521eb2d713be2421176/9465f6995793f958dfe2.json @@ -0,0 +1,46 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ConvBertModel", + "_task": "token-classification", + "architectures": [ + "ConvBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "conv_kernel_size": 9, + "dtype": "float32", + "embedding_size": 768, + "head_ratio": 2, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "convbert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "convbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_groups": 1, + "num_hidden_layers": 5, + "type_vocab_size": 16, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/53df05630467b607db56ffce08557c29099e045b32fc8d64867ed7ba1cb1a54d/77bc0b514397da45722a.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/53df05630467b607db56ffce08557c29099e045b32fc8d64867ed7ba1cb1a54d/77bc0b514397da45722a.json new file mode 100644 index 0000000000000000000000000000000000000000..24513ef08a05a95a66614832fa7e32d3ef4a3ed0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/53df05630467b607db56ffce08557c29099e045b32fc8d64867ed7ba1cb1a54d/77bc0b514397da45722a.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ElectraModel", + "_task": "question-answering", + "add_cross_attention": false, + "architectures": [ + "ElectraModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "electra", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "electra", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "summary_activation": "gelu", + "summary_last_dropout": 0.1, + "summary_type": "first", + "summary_use_proj": true, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/56fe21f6fe9cc7e845b907790962fbae299a132f0186c9afe7c7d4baa7fd0c36/03826091fa2f1e9e412e.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/56fe21f6fe9cc7e845b907790962fbae299a132f0186c9afe7c7d4baa7fd0c36/03826091fa2f1e9e412e.json new file mode 100644 index 0000000000000000000000000000000000000000..ae3e5e54c144910b489c61e8b8f81a5cbb1fe08e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/56fe21f6fe9cc7e845b907790962fbae299a132f0186c9afe7c7d4baa7fd0c36/03826091fa2f1e9e412e.json @@ -0,0 +1,42 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MPNetModel", + "_task": "text-classification", + "architectures": [ + "MPNetModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 64, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mpnet", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mpnet", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "relative_attention_num_buckets": 32, + "tie_word_embeddings": true, + "vocab_size": 1125 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/5aac472dfb6fd70fb6e6595c294549b70d96a2baa3a13c079945c10ea3a82bf0/03e8bbaa3b02c6e62ebc.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/5aac472dfb6fd70fb6e6595c294549b70d96a2baa3a13c079945c10ea3a82bf0/03e8bbaa3b02c6e62ebc.json new file mode 100644 index 0000000000000000000000000000000000000000..995c5d7a63d84c32aeb9e8515273b343aaa6ae34 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/5aac472dfb6fd70fb6e6595c294549b70d96a2baa3a13c079945c10ea3a82bf0/03e8bbaa3b02c6e62ebc.json @@ -0,0 +1,61 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-XLMModel", + "_task": "feature-extraction", + "architectures": [ + "XLMModel" + ], + "asm": false, + "attention_dropout": 0.1, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "mask_index": 5, + "mask_token_id": 5, + "max_position_embeddings": 512, + "model_type": "xlm", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "xlm", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "tie_word_embeddings": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": true, + "vocab_size": 30145 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/5aac472dfb6fd70fb6e6595c294549b70d96a2baa3a13c079945c10ea3a82bf0/e38e2c8e4b4d95e6d4eb.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/5aac472dfb6fd70fb6e6595c294549b70d96a2baa3a13c079945c10ea3a82bf0/e38e2c8e4b4d95e6d4eb.json new file mode 100644 index 0000000000000000000000000000000000000000..bd6a5cb868307b836ebc0436cb48c3b15d9fd384 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/5aac472dfb6fd70fb6e6595c294549b70d96a2baa3a13c079945c10ea3a82bf0/e38e2c8e4b4d95e6d4eb.json @@ -0,0 +1,61 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-XLMModel", + "_task": "feature-extraction", + "architectures": [ + "XLMModel" + ], + "asm": false, + "attention_dropout": 0.1, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "mask_index": 5, + "mask_token_id": 5, + "max_position_embeddings": 512, + "model_type": "xlm", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "xlm", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "tie_word_embeddings": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": true, + "vocab_size": 30145 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/5bfcb7c626c945694454abc9d38598c138e97883304ce6e19ef28a0a0f677641/cf1ecf075979b8253e98.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/5bfcb7c626c945694454abc9d38598c138e97883304ce6e19ef28a0a0f677641/cf1ecf075979b8253e98.json new file mode 100644 index 0000000000000000000000000000000000000000..d60507b468067f69367d9de2e063b894596ed37a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/5bfcb7c626c945694454abc9d38598c138e97883304ce6e19ef28a0a0f677641/cf1ecf075979b8253e98.json @@ -0,0 +1,48 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-camembert", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "CamembertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "camembert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "camembert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/5cc42a98dca6272d29d4af01c681cac23749dbcfcf00a6959cbecdd6d92a1192/5f14515ce10489e77f72.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/5cc42a98dca6272d29d4af01c681cac23749dbcfcf00a6959cbecdd6d92a1192/5f14515ce10489e77f72.json new file mode 100644 index 0000000000000000000000000000000000000000..e80c4cd616dc74f217603b7600348dac6b52116a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/5cc42a98dca6272d29d4af01c681cac23749dbcfcf00a6959cbecdd6d92a1192/5f14515ce10489e77f72.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DebertaModel", + "_task": "question-answering", + "architectures": [ + "DebertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-07, + "legacy": true, + "max_position_embeddings": 512, + "max_relative_positions": -1, + "model_type": "deberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "deberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "pooler_dropout": 0, + "pooler_hidden_act": "gelu", + "pooler_hidden_size": 32, + "pos_att_type": [ + "none" + ], + "position_biased_input": true, + "relative_attention": false, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 1024 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/5f42ea8b35fb6ef95e50f98a4c70868640ea933cd8f7d5482a1d838375c830a2/ace856aa22005340f899.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/5f42ea8b35fb6ef95e50f98a4c70868640ea933cd8f7d5482a1d838375c830a2/ace856aa22005340f899.json new file mode 100644 index 0000000000000000000000000000000000000000..9f85f1c9513572f54fdabf036d38174d292b7835 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/5f42ea8b35fb6ef95e50f98a4c70868640ea933cd8f7d5482a1d838375c830a2/ace856aa22005340f899.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DistilBertModel", + "_task": "text-classification", + "activation": "gelu", + "architectures": [ + "DistilBertModel" + ], + "attention_dropout": 0.1, + "dim": 32, + "dropout": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dim": 37, + "initializer_range": 0.02, + "max_position_embeddings": 512, + "model_type": "distilbert", + "n_heads": 4, + "n_layers": 5, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "distilbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "qa_dropout": 0.1, + "seq_classif_dropout": 0.2, + "sinusoidal_pos_embds": false, + "tie_word_embeddings": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/60bb2f3e59cfbb82bd42d8ab3f40d5745fc7e781557648b1b8dffeab8b4112bd/5d32954b22775bb0ced5.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/60bb2f3e59cfbb82bd42d8ab3f40d5745fc7e781557648b1b8dffeab8b4112bd/5d32954b22775bb0ced5.json new file mode 100644 index 0000000000000000000000000000000000000000..30fd9e1e0de998a1953e437a77ab54ec34ce3c53 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/60bb2f3e59cfbb82bd42d8ab3f40d5745fc7e781557648b1b8dffeab8b4112bd/5d32954b22775bb0ced5.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DistilBertModel", + "_task": "feature-extraction", + "activation": "gelu", + "architectures": [ + "DistilBertModel" + ], + "attention_dropout": 0.1, + "dim": 32, + "dropout": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dim": 37, + "initializer_range": 0.02, + "max_position_embeddings": 512, + "model_type": "distilbert", + "n_heads": 4, + "n_layers": 5, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "distilbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "qa_dropout": 0.1, + "seq_classif_dropout": 0.2, + "sinusoidal_pos_embds": false, + "tie_word_embeddings": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/60bb2f3e59cfbb82bd42d8ab3f40d5745fc7e781557648b1b8dffeab8b4112bd/e619a909fa012f49ce83.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/60bb2f3e59cfbb82bd42d8ab3f40d5745fc7e781557648b1b8dffeab8b4112bd/e619a909fa012f49ce83.json new file mode 100644 index 0000000000000000000000000000000000000000..2c948934e058a46e92bae85a0fc116a204847119 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/60bb2f3e59cfbb82bd42d8ab3f40d5745fc7e781557648b1b8dffeab8b4112bd/e619a909fa012f49ce83.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DistilBertModel", + "_task": "feature-extraction", + "activation": "gelu", + "architectures": [ + "DistilBertModel" + ], + "attention_dropout": 0.1, + "dim": 32, + "dropout": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dim": 37, + "initializer_range": 0.02, + "max_position_embeddings": 512, + "model_type": "distilbert", + "n_heads": 4, + "n_layers": 5, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "distilbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "qa_dropout": 0.1, + "seq_classif_dropout": 0.2, + "sinusoidal_pos_embds": false, + "tie_word_embeddings": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/62030a5425d8521109f5082f87b76366c30656ddda84c83ce627d8e5bf60e3d6/c1fbdd662b44ccffde91.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/62030a5425d8521109f5082f87b76366c30656ddda84c83ce627d8e5bf60e3d6/c1fbdd662b44ccffde91.json new file mode 100644 index 0000000000000000000000000000000000000000..560fcb9a0e6c38fb841455c7d6c62b07c2e1c715 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/62030a5425d8521109f5082f87b76366c30656ddda84c83ce627d8e5bf60e3d6/c1fbdd662b44ccffde91.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "question-answering", + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6370f7f7edebe0f11997389e6b736b0e04254dc884f7403096082b0256aebaf0/98dc6e683d0d84656526.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6370f7f7edebe0f11997389e6b736b0e04254dc884f7403096082b0256aebaf0/98dc6e683d0d84656526.json new file mode 100644 index 0000000000000000000000000000000000000000..fe44814bcfbefc0d68ba345e8ecd0a6fc933e0dd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6370f7f7edebe0f11997389e6b736b0e04254dc884f7403096082b0256aebaf0/98dc6e683d0d84656526.json @@ -0,0 +1,49 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ConvBertModel", + "_task": "token-classification", + "add_cross_attention": false, + "architectures": [ + "ConvBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "conv_kernel_size": 9, + "dtype": "float32", + "embedding_size": 768, + "head_ratio": 2, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "convbert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "convbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_groups": 1, + "num_hidden_layers": 5, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6632a982ca4fad30da92c0b9be0224cff16749b6032bf31c180b0175e4bf4b44/04b5c83958ebb7367afa.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6632a982ca4fad30da92c0b9be0224cff16749b6032bf31c180b0175e4bf4b44/04b5c83958ebb7367afa.json new file mode 100644 index 0000000000000000000000000000000000000000..815f2be0217c222507e9ae76f7bebc3245747772 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6632a982ca4fad30da92c0b9be0224cff16749b6032bf31c180b0175e4bf4b44/04b5c83958ebb7367afa.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DebertaModel", + "_task": "fill-mask", + "architectures": [ + "DebertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-07, + "legacy": true, + "max_position_embeddings": 512, + "max_relative_positions": -1, + "model_type": "deberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "deberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "pooler_dropout": 0, + "pooler_hidden_act": "gelu", + "pooler_hidden_size": 32, + "pos_att_type": [ + "none" + ], + "position_biased_input": true, + "relative_attention": false, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 1024 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/69a0003a65cbb13aa1a07e190e0bcc5ba62b0cfe5fd23cd466e9abe700a23f88/83b4f4f21dbb86e2a347.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/69a0003a65cbb13aa1a07e190e0bcc5ba62b0cfe5fd23cd466e9abe700a23f88/83b4f4f21dbb86e2a347.json new file mode 100644 index 0000000000000000000000000000000000000000..35620113533ab5cca84bd55f8226d75cff70bcb0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/69a0003a65cbb13aa1a07e190e0bcc5ba62b0cfe5fd23cd466e9abe700a23f88/83b4f4f21dbb86e2a347.json @@ -0,0 +1,49 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ElectraModel", + "_task": "text-classification", + "architectures": [ + "ElectraModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "electra", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "electra", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "summary_activation": "gelu", + "summary_last_dropout": 0.1, + "summary_type": "first", + "summary_use_proj": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/69da8f58c62bbda433db09f1735435dfd704c8fae8ba761dddc359b26681f060/57adccd831024740b4f4.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/69da8f58c62bbda433db09f1735435dfd704c8fae8ba761dddc359b26681f060/57adccd831024740b4f4.json new file mode 100644 index 0000000000000000000000000000000000000000..b7f7e9b47323766a4cb19715ff9ee6fb732cf96f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/69da8f58c62bbda433db09f1735435dfd704c8fae8ba761dddc359b26681f060/57adccd831024740b4f4.json @@ -0,0 +1,46 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ConvBertModel", + "_task": "question-answering", + "architectures": [ + "ConvBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "conv_kernel_size": 9, + "dtype": "float32", + "embedding_size": 768, + "head_ratio": 2, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "convbert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "convbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_groups": 1, + "num_hidden_layers": 5, + "type_vocab_size": 16, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/71237af09ba9ec1d8ac16234edce0e58637a56a58f5a850c92e189743063976e/2072af6259d58bf3fb87.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/71237af09ba9ec1d8ac16234edce0e58637a56a58f5a850c92e189743063976e/2072af6259d58bf3fb87.json new file mode 100644 index 0000000000000000000000000000000000000000..7058811829229c73284485b463e172b59a6b7da2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/71237af09ba9ec1d8ac16234edce0e58637a56a58f5a850c92e189743063976e/2072af6259d58bf3fb87.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "fill-mask", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/71237af09ba9ec1d8ac16234edce0e58637a56a58f5a850c92e189743063976e/8b760d973cb7584e4b45.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/71237af09ba9ec1d8ac16234edce0e58637a56a58f5a850c92e189743063976e/8b760d973cb7584e4b45.json new file mode 100644 index 0000000000000000000000000000000000000000..07ecac482c1561d8474da205ef39cb833ba7693a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/71237af09ba9ec1d8ac16234edce0e58637a56a58f5a850c92e189743063976e/8b760d973cb7584e4b45.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "fill-mask", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/71237af09ba9ec1d8ac16234edce0e58637a56a58f5a850c92e189743063976e/bd7f009eb4b7bff83b7f.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/71237af09ba9ec1d8ac16234edce0e58637a56a58f5a850c92e189743063976e/bd7f009eb4b7bff83b7f.json new file mode 100644 index 0000000000000000000000000000000000000000..5c42e72174afac6e8048631fcd1f880ca4300d5e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/71237af09ba9ec1d8ac16234edce0e58637a56a58f5a850c92e189743063976e/bd7f009eb4b7bff83b7f.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "fill-mask", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/71afe1394887790a6a9c9b43a4cffb83f1fae1b370d45c21fe0069af4be416f7/ce615daa5db83c251d86.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/71afe1394887790a6a9c9b43a4cffb83f1fae1b370d45c21fe0069af4be416f7/ce615daa5db83c251d86.json new file mode 100644 index 0000000000000000000000000000000000000000..17f3da19c1ac40695851cdd6287685c9fed86b43 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/71afe1394887790a6a9c9b43a4cffb83f1fae1b370d45c21fe0069af4be416f7/ce615daa5db83c251d86.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "dtype": "float16", + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "rope_theta": 10000.0, + "rope_type": "default" + }, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/72be3564bc520098a843c94b44441c11a43f363f6ab861266b21eb629e39cb38/83173c922ca41f9580b7.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/72be3564bc520098a843c94b44441c11a43f363f6ab861266b21eb629e39cb38/83173c922ca41f9580b7.json new file mode 100644 index 0000000000000000000000000000000000000000..ec8ad9ae70606436650cc3a19c71feacfadf09e8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/72be3564bc520098a843c94b44441c11a43f363f6ab861266b21eb629e39cb38/83173c922ca41f9580b7.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-flaubert", + "_task": "text-classification", + "architectures": [ + "FlaubertModel" + ], + "asm": false, + "attention_dropout": 0.1, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "layerdrop": 0.0, + "mask_index": 5, + "mask_token_id": 0, + "max_position_embeddings": 512, + "model_type": "flaubert", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "flaubert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "pre_norm": false, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "tie_word_embeddings": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": null, + "vocab_size": 68729 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/744918028556eb239a0e6ae79a7594cc0ffdd594076b78297fd13c80e9974ef8/58d796b9cd3b8d7bfb9e.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/744918028556eb239a0e6ae79a7594cc0ffdd594076b78297fd13c80e9974ef8/58d796b9cd3b8d7bfb9e.json new file mode 100644 index 0000000000000000000000000000000000000000..d05b7eb9c1cf7a07bbe8045d517f9a9d3235f816 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/744918028556eb239a0e6ae79a7594cc0ffdd594076b78297fd13c80e9974ef8/58d796b9cd3b8d7bfb9e.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RoFormerModel", + "_task": "token-classification", + "architectures": [ + "RoFormerModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roformer", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roformer", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "rotary_value": false, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 50000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7763ffbcc3bb1a712ccf49ba4e34ea7185ce1aafd9a666c83343fdc4f332bd35/cd736fae56ac1108ac81.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7763ffbcc3bb1a712ccf49ba4e34ea7185ce1aafd9a666c83343fdc4f332bd35/cd736fae56ac1108ac81.json new file mode 100644 index 0000000000000000000000000000000000000000..c81fe8cd7f6562f84da1daef5d5437164b06bfc2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7763ffbcc3bb1a712ccf49ba4e34ea7185ce1aafd9a666c83343fdc4f332bd35/cd736fae56ac1108ac81.json @@ -0,0 +1,46 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "fill-mask", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7775eda06f097899ad5c292638a3a63f89448ede9e4c866a53339ffc7d230b8a/049b5c49381bd1746986.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7775eda06f097899ad5c292638a3a63f89448ede9e4c866a53339ffc7d230b8a/049b5c49381bd1746986.json new file mode 100644 index 0000000000000000000000000000000000000000..e3495b7feabf48da1f55b8108855d0f54f8ba51c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7775eda06f097899ad5c292638a3a63f89448ede9e4c866a53339ffc7d230b8a/049b5c49381bd1746986.json @@ -0,0 +1,45 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-camembert", + "_task": "text-classification", + "architectures": [ + "CamembertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "camembert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "camembert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7874095b8afd63bcd7878230b50ab3fd3fb3167bc4865d581956529e864d67af/643554f31cfe71c82427.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7874095b8afd63bcd7878230b50ab3fd3fb3167bc4865d581956529e864d67af/643554f31cfe71c82427.json new file mode 100644 index 0000000000000000000000000000000000000000..2e191f335e4f6b9b325fde4756002bf0222669f1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7874095b8afd63bcd7878230b50ab3fd3fb3167bc4865d581956529e864d67af/643554f31cfe71c82427.json @@ -0,0 +1,61 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "dtype": "float32", + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 10000.0, + "rope_type": "default" + }, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7c5ac13a8ac6a4619cf99a96e4f866abe69a648c259c53e7287e874d901c2b78/7f1559c80a7c99cc16a6.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7c5ac13a8ac6a4619cf99a96e4f866abe69a648c259c53e7287e874d901c2b78/7f1559c80a7c99cc16a6.json new file mode 100644 index 0000000000000000000000000000000000000000..c4dd5a5ac71e799369832dc2d88e86346741118c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7c5ac13a8ac6a4619cf99a96e4f866abe69a648c259c53e7287e874d901c2b78/7f1559c80a7c99cc16a6.json @@ -0,0 +1,61 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-XLMModel", + "_task": "fill-mask", + "architectures": [ + "XLMModel" + ], + "asm": false, + "attention_dropout": 0.1, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "mask_index": 5, + "mask_token_id": 5, + "max_position_embeddings": 512, + "model_type": "xlm", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "xlm", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "tie_word_embeddings": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": true, + "vocab_size": 30145 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7c5ac13a8ac6a4619cf99a96e4f866abe69a648c259c53e7287e874d901c2b78/8d9eca353e1b88bf975e.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7c5ac13a8ac6a4619cf99a96e4f866abe69a648c259c53e7287e874d901c2b78/8d9eca353e1b88bf975e.json new file mode 100644 index 0000000000000000000000000000000000000000..7977c0a3e9cb443fb2a71ebdf1fce4d1dfac1fc8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7c5ac13a8ac6a4619cf99a96e4f866abe69a648c259c53e7287e874d901c2b78/8d9eca353e1b88bf975e.json @@ -0,0 +1,61 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-XLMModel", + "_task": "fill-mask", + "architectures": [ + "XLMModel" + ], + "asm": false, + "attention_dropout": 0.1, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "mask_index": 5, + "mask_token_id": 5, + "max_position_embeddings": 512, + "model_type": "xlm", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "xlm", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "tie_word_embeddings": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": true, + "vocab_size": 30145 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7c86dcd3f0c9b2bb7d966288ee02ce6efda5bca26d1052b6844847447cc61aa0/2d3e547ebbc6fff4f957.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7c86dcd3f0c9b2bb7d966288ee02ce6efda5bca26d1052b6844847447cc61aa0/2d3e547ebbc6fff4f957.json new file mode 100644 index 0000000000000000000000000000000000000000..40e37c48f4d1ed26aa0c798162ba173f20509936 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7c86dcd3f0c9b2bb7d966288ee02ce6efda5bca26d1052b6844847447cc61aa0/2d3e547ebbc6fff4f957.json @@ -0,0 +1,46 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ConvBertModel", + "_task": "text-classification", + "architectures": [ + "ConvBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "conv_kernel_size": 9, + "dtype": "float32", + "embedding_size": 768, + "head_ratio": 2, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "convbert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "convbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_groups": 1, + "num_hidden_layers": 5, + "type_vocab_size": 16, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7cc2aee60f33cc55bb59c1166c6baf36bd5e5dbffc63a8b65c9aa7eaf2cec0a0/42fb5b9025ad50931cbf.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7cc2aee60f33cc55bb59c1166c6baf36bd5e5dbffc63a8b65c9aa7eaf2cec0a0/42fb5b9025ad50931cbf.json new file mode 100644 index 0000000000000000000000000000000000000000..6753aa0c5508eabba457b63588e270702f31c316 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7cc2aee60f33cc55bb59c1166c6baf36bd5e5dbffc63a8b65c9aa7eaf2cec0a0/42fb5b9025ad50931cbf.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "text-classification", + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": false, + "instance_type": "inf2", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 16, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7cc2aee60f33cc55bb59c1166c6baf36bd5e5dbffc63a8b65c9aa7eaf2cec0a0/56d9d8236b3867ca0321.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7cc2aee60f33cc55bb59c1166c6baf36bd5e5dbffc63a8b65c9aa7eaf2cec0a0/56d9d8236b3867ca0321.json new file mode 100644 index 0000000000000000000000000000000000000000..677960e0c6317bfd0b0930e22c3a3800ca364f1c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7cc2aee60f33cc55bb59c1166c6baf36bd5e5dbffc63a8b65c9aa7eaf2cec0a0/56d9d8236b3867ca0321.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "text-classification", + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7e4f5a794c6e311b521ace3054ccb34f0dd8eba1aa2da250fb05c39200b492d1/da846a883f4635d1b097.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7e4f5a794c6e311b521ace3054ccb34f0dd8eba1aa2da250fb05c39200b492d1/da846a883f4635d1b097.json new file mode 100644 index 0000000000000000000000000000000000000000..0f5a10d266b50564c1a55a88401a91be3146f071 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7e4f5a794c6e311b521ace3054ccb34f0dd8eba1aa2da250fb05c39200b492d1/da846a883f4635d1b097.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RoFormerModel", + "_task": "text-classification", + "architectures": [ + "RoFormerModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roformer", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roformer", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "rotary_value": false, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 50000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7f7f63b7277ae113987a8606d325290319781f6c740bb78512d3f4c903174287/efbf3a0d9f80027e2470.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7f7f63b7277ae113987a8606d325290319781f6c740bb78512d3f4c903174287/efbf3a0d9f80027e2470.json new file mode 100644 index 0000000000000000000000000000000000000000..720e277a58cb5d68a1b9240905916d58fee26f2b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7f7f63b7277ae113987a8606d325290319781f6c740bb78512d3f4c903174287/efbf3a0d9f80027e2470.json @@ -0,0 +1,64 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_theta": 500000.0, + "rope_type": "llama3" + }, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7ff81c7781ea167fc6697a20d9f4ac69c90967f22eba36eb4b3efa7a876f7d4c/fe3e160e1d40a57df793.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7ff81c7781ea167fc6697a20d9f4ac69c90967f22eba36eb4b3efa7a876f7d4c/fe3e160e1d40a57df793.json new file mode 100644 index 0000000000000000000000000000000000000000..d4768882dd26137de7ac6bc67ea26d50696a7612 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/7ff81c7781ea167fc6697a20d9f4ac69c90967f22eba36eb4b3efa7a876f7d4c/fe3e160e1d40a57df793.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RobertaModel", + "_task": "text-classification", + "architectures": [ + "RobertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1024 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/804240cd6d1c081d10c54cde9974589667be796d0031aa591ffbb98b373a3829/b52ba06aa5dd84b77765.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/804240cd6d1c081d10c54cde9974589667be796d0031aa591ffbb98b373a3829/b52ba06aa5dd84b77765.json new file mode 100644 index 0000000000000000000000000000000000000000..b5987fb20ae98e5a2f37dee7f9fa75a7d1f7b544 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/804240cd6d1c081d10c54cde9974589667be796d0031aa591ffbb98b373a3829/b52ba06aa5dd84b77765.json @@ -0,0 +1,65 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "layer_types": [ + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_theta": 1000000.0, + "rope_type": "yarn", + "type": "yarn" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/82c245b0c8ebc29618beac5459dec7519999d03ace18702291e4375aa47076e4/5293253c6647ff5e1226.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/82c245b0c8ebc29618beac5459dec7519999d03ace18702291e4375aa47076e4/5293253c6647ff5e1226.json new file mode 100644 index 0000000000000000000000000000000000000000..80df479eb1ac55c34f20091e7b4a55a6c9fb1af4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/82c245b0c8ebc29618beac5459dec7519999d03ace18702291e4375aa47076e4/5293253c6647ff5e1226.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ElectraModel", + "_task": "fill-mask", + "add_cross_attention": false, + "architectures": [ + "ElectraModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "electra", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "electra", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "summary_activation": "gelu", + "summary_last_dropout": 0.1, + "summary_type": "first", + "summary_use_proj": true, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/82c245b0c8ebc29618beac5459dec7519999d03ace18702291e4375aa47076e4/dcea8e84086a8eb4b3f7.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/82c245b0c8ebc29618beac5459dec7519999d03ace18702291e4375aa47076e4/dcea8e84086a8eb4b3f7.json new file mode 100644 index 0000000000000000000000000000000000000000..c6f767330162efd377bfd0814fe2de056030b018 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/82c245b0c8ebc29618beac5459dec7519999d03ace18702291e4375aa47076e4/dcea8e84086a8eb4b3f7.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ElectraModel", + "_task": "fill-mask", + "add_cross_attention": false, + "architectures": [ + "ElectraModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "electra", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "electra", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "summary_activation": "gelu", + "summary_last_dropout": 0.1, + "summary_type": "first", + "summary_use_proj": true, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8853a992c9dba8a3b97c87c2f3aa9d65ca454d774b931b92b886a5d740af32d6/2b5ba8600a7737814044.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8853a992c9dba8a3b97c87c2f3aa9d65ca454d774b931b92b886a5d740af32d6/2b5ba8600a7737814044.json new file mode 100644 index 0000000000000000000000000000000000000000..88c5c4294b1c5545da6ad87e14ca781e309f0d7d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8853a992c9dba8a3b97c87c2f3aa9d65ca454d774b931b92b886a5d740af32d6/2b5ba8600a7737814044.json @@ -0,0 +1,43 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DistilBertModel", + "_task": "token-classification", + "activation": "gelu", + "architectures": [ + "DistilBertModel" + ], + "attention_dropout": 0.1, + "dim": 32, + "dropout": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dim": 37, + "initializer_range": 0.02, + "max_position_embeddings": 512, + "model_type": "distilbert", + "n_heads": 4, + "n_layers": 5, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "distilbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "qa_dropout": 0.1, + "seq_classif_dropout": 0.2, + "sinusoidal_pos_embds": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/88f0fc49d11ba84a192e1b0b9bbbeca5d0269dcbd215f4b8a129b03981de7ac7/a4d579f0a999f0995aff.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/88f0fc49d11ba84a192e1b0b9bbbeca5d0269dcbd215f4b8a129b03981de7ac7/a4d579f0a999f0995aff.json new file mode 100644 index 0000000000000000000000000000000000000000..9974325b9fbe846dc096bf3b27f56265c55de064 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/88f0fc49d11ba84a192e1b0b9bbbeca5d0269dcbd215f4b8a129b03981de7ac7/a4d579f0a999f0995aff.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-XLMModel", + "_task": "text-classification", + "architectures": [ + "XLMModel" + ], + "asm": false, + "attention_dropout": 0.1, + "bos_index": 0, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "eos_index": 1, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "mask_index": 5, + "mask_token_id": 5, + "max_position_embeddings": 512, + "model_type": "xlm", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "xlm", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "pad_index": 2, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": true, + "vocab_size": 30145 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8a71c93374c410c68c20f6d7c2cbc81992d06190fad2fa8b00c76974ee8224f7/6b99fcaeafebd4b56d33.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8a71c93374c410c68c20f6d7c2cbc81992d06190fad2fa8b00c76974ee8224f7/6b99fcaeafebd4b56d33.json new file mode 100644 index 0000000000000000000000000000000000000000..04000ccdb9e3eb06ebafe3fa61880fb59c5cd807 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8a71c93374c410c68c20f6d7c2cbc81992d06190fad2fa8b00c76974ee8224f7/6b99fcaeafebd4b56d33.json @@ -0,0 +1,49 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "sentence-transformers/all-MiniLM-L6-v2", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "export_model_type": "transformer", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 384, + "initializer_range": 0.02, + "intermediate_size": 1536, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "transformer", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 12, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 2, + "use_cache": true, + "vocab_size": 30522 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8a71c93374c410c68c20f6d7c2cbc81992d06190fad2fa8b00c76974ee8224f7/949da88be1660765ad17.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8a71c93374c410c68c20f6d7c2cbc81992d06190fad2fa8b00c76974ee8224f7/949da88be1660765ad17.json new file mode 100644 index 0000000000000000000000000000000000000000..5ef5547c3223abf86e896fdd9ea71d0c20b7a1df --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8a71c93374c410c68c20f6d7c2cbc81992d06190fad2fa8b00c76974ee8224f7/949da88be1660765ad17.json @@ -0,0 +1,49 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "sentence-transformers/all-MiniLM-L6-v2", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "export_model_type": "transformer", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 384, + "initializer_range": 0.02, + "intermediate_size": 1536, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "transformer", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 16, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 12, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 2, + "use_cache": true, + "vocab_size": 30522 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8c0f11c53719faf15260bb1c1bb4d74c0b64a1afe41c0c11aba03f3b54d79e25/9ab19a441de3dfd2f259.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8c0f11c53719faf15260bb1c1bb4d74c0b64a1afe41c0c11aba03f3b54d79e25/9ab19a441de3dfd2f259.json new file mode 100644 index 0000000000000000000000000000000000000000..80aee40619fcb54a89ab4a4a3e90188028d13739 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8c0f11c53719faf15260bb1c1bb4d74c0b64a1afe41c0c11aba03f3b54d79e25/9ab19a441de3dfd2f259.json @@ -0,0 +1,48 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-camembert", + "_task": "question-answering", + "add_cross_attention": false, + "architectures": [ + "CamembertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "camembert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "camembert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8c5628872d9161c25a42bdf7b91dc9d06d62959f183ad858dde6f3056d17a4df/8acc64ea4d1a424441ec.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8c5628872d9161c25a42bdf7b91dc9d06d62959f183ad858dde6f3056d17a4df/8acc64ea4d1a424441ec.json new file mode 100644 index 0000000000000000000000000000000000000000..06f45ff115f0cb23bad99394209326dab853814b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8c5628872d9161c25a42bdf7b91dc9d06d62959f183ad858dde6f3056d17a4df/8acc64ea4d1a424441ec.json @@ -0,0 +1,43 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DistilBertModel", + "_task": "text-classification", + "activation": "gelu", + "architectures": [ + "DistilBertModel" + ], + "attention_dropout": 0.1, + "dim": 32, + "dropout": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dim": 37, + "initializer_range": 0.02, + "max_position_embeddings": 512, + "model_type": "distilbert", + "n_heads": 4, + "n_layers": 5, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "distilbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "qa_dropout": 0.1, + "seq_classif_dropout": 0.2, + "sinusoidal_pos_embds": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8c7ee896cff9535430d8421a7fd298e2321ab280c05b8f5fc12c7247a52235f0/128a69453ac648a09d14.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8c7ee896cff9535430d8421a7fd298e2321ab280c05b8f5fc12c7247a52235f0/128a69453ac648a09d14.json new file mode 100644 index 0000000000000000000000000000000000000000..6406d7d11ef3b71cf9146cf39bd265d9d818e24d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8c7ee896cff9535430d8421a7fd298e2321ab280c05b8f5fc12c7247a52235f0/128a69453ac648a09d14.json @@ -0,0 +1,49 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ElectraModel", + "_task": "question-answering", + "architectures": [ + "ElectraModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "electra", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "electra", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "summary_activation": "gelu", + "summary_last_dropout": 0.1, + "summary_type": "first", + "summary_use_proj": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8c8e36e7a2fdbf0359e8fa765751eed060c0bec67d42841c3f6a1a72f6b4f07c/3a6a997eb9ac299901af.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8c8e36e7a2fdbf0359e8fa765751eed060c0bec67d42841c3f6a1a72f6b4f07c/3a6a997eb9ac299901af.json new file mode 100644 index 0000000000000000000000000000000000000000..28d261a588d32fda89eab18b80afa62e5025ab51 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8c8e36e7a2fdbf0359e8fa765751eed060c0bec67d42841c3f6a1a72f6b4f07c/3a6a997eb9ac299901af.json @@ -0,0 +1,49 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ElectraModel", + "_task": "token-classification", + "architectures": [ + "ElectraModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "electra", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "electra", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "summary_activation": "gelu", + "summary_last_dropout": 0.1, + "summary_type": "first", + "summary_use_proj": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8e95b42a40618bb4c5591b3e307b6b6f7b50214b219f40328765171fe12b6366/4adfc5a46ae499e66ae8.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8e95b42a40618bb4c5591b3e307b6b6f7b50214b219f40328765171fe12b6366/4adfc5a46ae499e66ae8.json new file mode 100644 index 0000000000000000000000000000000000000000..96b001ea9142dd818752ae38920f7605c2251071 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8e95b42a40618bb4c5591b3e307b6b6f7b50214b219f40328765171fe12b6366/4adfc5a46ae499e66ae8.json @@ -0,0 +1,46 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "question-answering", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8efa45baeed80c7e8fac8714b979eba867fa5e392f4e06457bee56ea0f62a643/642c135a5c1d974a43e2.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8efa45baeed80c7e8fac8714b979eba867fa5e392f4e06457bee56ea0f62a643/642c135a5c1d974a43e2.json new file mode 100644 index 0000000000000000000000000000000000000000..792dc2ca96cff3b6b8285cefb12785c448e1b8bb --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8efa45baeed80c7e8fac8714b979eba867fa5e392f4e06457bee56ea0f62a643/642c135a5c1d974a43e2.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RobertaModel", + "_task": "question-answering", + "architectures": [ + "RobertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1024 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8f76b1d6bf59fe388151c6144b094c1744a188e47cb51d4a46889114095b1302/001735c65eb958259350.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8f76b1d6bf59fe388151c6144b094c1744a188e47cb51d4a46889114095b1302/001735c65eb958259350.json new file mode 100644 index 0000000000000000000000000000000000000000..cc262a23261237c839137e7b16178f00ba27a281 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8f76b1d6bf59fe388151c6144b094c1744a188e47cb51d4a46889114095b1302/001735c65eb958259350.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "float16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 512, + "max_topk": 256, + "n_active_tokens": 512, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 512, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_theta": 500000.0, + "rope_type": "llama3" + }, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8f76b1d6bf59fe388151c6144b094c1744a188e47cb51d4a46889114095b1302/b05bb5afbe9b9c43035d.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8f76b1d6bf59fe388151c6144b094c1744a188e47cb51d4a46889114095b1302/b05bb5afbe9b9c43035d.json new file mode 100644 index 0000000000000000000000000000000000000000..178b6edde9d364d50d772ac570302270dae8bb7f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8f76b1d6bf59fe388151c6144b094c1744a188e47cb51d4a46889114095b1302/b05bb5afbe9b9c43035d.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "float16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_theta": 500000.0, + "rope_type": "llama3" + }, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8f76b1d6bf59fe388151c6144b094c1744a188e47cb51d4a46889114095b1302/f0fb2666b764ccbb1337.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8f76b1d6bf59fe388151c6144b094c1744a188e47cb51d4a46889114095b1302/f0fb2666b764ccbb1337.json new file mode 100644 index 0000000000000000000000000000000000000000..4e244b282218ac5f8c956db62006e24d10ed74cd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/8f76b1d6bf59fe388151c6144b094c1744a188e47cb51d4a46889114095b1302/f0fb2666b764ccbb1337.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "float16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 128, + "max_topk": 256, + "n_active_tokens": 128, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 128, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_theta": 500000.0, + "rope_type": "llama3" + }, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9281219974499ef93e221903ba4eccae94588e8d3b91b1a1305ad7bc5a95ab56/011a54ba72935a0def5a.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9281219974499ef93e221903ba4eccae94588e8d3b91b1a1305ad7bc5a95ab56/011a54ba72935a0def5a.json new file mode 100644 index 0000000000000000000000000000000000000000..5f676bca654b575c74494e5c34689bdc89b89463 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9281219974499ef93e221903ba4eccae94588e8d3b91b1a1305ad7bc5a95ab56/011a54ba72935a0def5a.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RobertaModel", + "_task": "fill-mask", + "add_cross_attention": false, + "architectures": [ + "RobertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1024 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9281219974499ef93e221903ba4eccae94588e8d3b91b1a1305ad7bc5a95ab56/97da11286be28a15760d.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9281219974499ef93e221903ba4eccae94588e8d3b91b1a1305ad7bc5a95ab56/97da11286be28a15760d.json new file mode 100644 index 0000000000000000000000000000000000000000..f9488af95e7d46ed2a3de1829262ccc724e556c8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9281219974499ef93e221903ba4eccae94588e8d3b91b1a1305ad7bc5a95ab56/97da11286be28a15760d.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RobertaModel", + "_task": "fill-mask", + "add_cross_attention": false, + "architectures": [ + "RobertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1024 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/940fa388275eb7c5d6c9023730c1b03a5f9332841564d21b1e5a8b595c87bc2a/d18ffb0d2a669a8b23da.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/940fa388275eb7c5d6c9023730c1b03a5f9332841564d21b1e5a8b595c87bc2a/d18ffb0d2a669a8b23da.json new file mode 100644 index 0000000000000000000000000000000000000000..58a68530abb8c2433e524a347fa3c15ef60b7172 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/940fa388275eb7c5d6c9023730c1b03a5f9332841564d21b1e5a8b595c87bc2a/d18ffb0d2a669a8b23da.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MobileBertModel", + "_task": "question-answering", + "architectures": [ + "MobileBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_activation": true, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 37, + "intra_bottleneck_size": 128, + "key_query_shared_bottleneck": true, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mobilebert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mobilebert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "normalization_type": "no_norm", + "num_attention_heads": 4, + "num_feedforward_networks": 4, + "num_hidden_layers": 5, + "tie_word_embeddings": true, + "trigram_input": true, + "true_hidden_size": 128, + "type_vocab_size": 16, + "use_bottleneck": true, + "use_bottleneck_attention": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/975ca10fcf34489fbaf3f186cd58ba10d6abc4b91d758ce9700626365252e572/1440cca519eae3b70d49.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/975ca10fcf34489fbaf3f186cd58ba10d6abc4b91d758ce9700626365252e572/1440cca519eae3b70d49.json new file mode 100644 index 0000000000000000000000000000000000000000..7bb8363de8648ce50c02f3f80ecf0fefa3e0edd8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/975ca10fcf34489fbaf3f186cd58ba10d6abc4b91d758ce9700626365252e572/1440cca519eae3b70d49.json @@ -0,0 +1,41 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MPNetModel", + "_task": "fill-mask", + "architectures": [ + "MPNetModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 64, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mpnet", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mpnet", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "relative_attention_num_buckets": 32, + "vocab_size": 1125 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/97cb742cd92d15c3182c43cb4b1d23516467e8e6e6ad80337fd1f43900471c1b/867f78fb306d62938dd8.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/97cb742cd92d15c3182c43cb4b1d23516467e8e6e6ad80337fd1f43900471c1b/867f78fb306d62938dd8.json new file mode 100644 index 0000000000000000000000000000000000000000..c2cc9443087ec6bbc502784d950b62506eab93c7 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/97cb742cd92d15c3182c43cb4b1d23516467e8e6e6ad80337fd1f43900471c1b/867f78fb306d62938dd8.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DebertaV2Model", + "_task": "feature-extraction", + "architectures": [ + "DebertaV2Model" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-07, + "legacy": true, + "max_position_embeddings": 512, + "max_relative_positions": -1, + "model_type": "deberta-v2", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "deberta-v2", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "pooler_dropout": 0, + "pooler_hidden_act": "gelu", + "pooler_hidden_size": 32, + "pos_att_type": [ + "none" + ], + "position_biased_input": true, + "relative_attention": false, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 128001 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9b2628f261397d060f20102d0abdd68f3bdd5141273c5e7f55c5024d1bfb6de0/02f614644042a7cafc7f.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9b2628f261397d060f20102d0abdd68f3bdd5141273c5e7f55c5024d1bfb6de0/02f614644042a7cafc7f.json new file mode 100644 index 0000000000000000000000000000000000000000..573a42fcf4df6aaadcedb6b374bf787bf460250d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9b2628f261397d060f20102d0abdd68f3bdd5141273c5e7f55c5024d1bfb6de0/02f614644042a7cafc7f.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "question-answering", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9b2628f261397d060f20102d0abdd68f3bdd5141273c5e7f55c5024d1bfb6de0/4a1ecc6b25efa2503b2b.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9b2628f261397d060f20102d0abdd68f3bdd5141273c5e7f55c5024d1bfb6de0/4a1ecc6b25efa2503b2b.json new file mode 100644 index 0000000000000000000000000000000000000000..4a21ca600b7c584e0ff63ebd71237795d154c169 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9b2628f261397d060f20102d0abdd68f3bdd5141273c5e7f55c5024d1bfb6de0/4a1ecc6b25efa2503b2b.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "question-answering", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9e88afec21cd6187a7f868941d2a9f90d77134e2ef5ad81ed7323afaa9cc8f07/7f8b4c79f38854eaa342.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9e88afec21cd6187a7f868941d2a9f90d77134e2ef5ad81ed7323afaa9cc8f07/7f8b4c79f38854eaa342.json new file mode 100644 index 0000000000000000000000000000000000000000..26875579a7ef56717d5183401ced67e8673af57c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9e88afec21cd6187a7f868941d2a9f90d77134e2ef5ad81ed7323afaa9cc8f07/7f8b4c79f38854eaa342.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MobileBertModel", + "_task": "feature-extraction", + "architectures": [ + "MobileBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_activation": true, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 37, + "intra_bottleneck_size": 128, + "key_query_shared_bottleneck": true, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mobilebert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mobilebert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "normalization_type": "no_norm", + "num_attention_heads": 4, + "num_feedforward_networks": 4, + "num_hidden_layers": 5, + "tie_word_embeddings": true, + "trigram_input": true, + "true_hidden_size": 128, + "type_vocab_size": 16, + "use_bottleneck": true, + "use_bottleneck_attention": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9e88afec21cd6187a7f868941d2a9f90d77134e2ef5ad81ed7323afaa9cc8f07/a6e9d57ec820a3f2d6c5.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9e88afec21cd6187a7f868941d2a9f90d77134e2ef5ad81ed7323afaa9cc8f07/a6e9d57ec820a3f2d6c5.json new file mode 100644 index 0000000000000000000000000000000000000000..bd2b47b8b427ac73735df0c2cb97613dfcfb60fc --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9e88afec21cd6187a7f868941d2a9f90d77134e2ef5ad81ed7323afaa9cc8f07/a6e9d57ec820a3f2d6c5.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MobileBertModel", + "_task": "feature-extraction", + "architectures": [ + "MobileBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_activation": true, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 37, + "intra_bottleneck_size": 128, + "key_query_shared_bottleneck": true, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mobilebert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mobilebert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "normalization_type": "no_norm", + "num_attention_heads": 4, + "num_feedforward_networks": 4, + "num_hidden_layers": 5, + "tie_word_embeddings": true, + "trigram_input": true, + "true_hidden_size": 128, + "type_vocab_size": 16, + "use_bottleneck": true, + "use_bottleneck_attention": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9f58df9cfff5526c47d9483ba90a26f5535cb01f04c479e653df888d0c39386a/312cc00672f6ea6a2091.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9f58df9cfff5526c47d9483ba90a26f5535cb01f04c479e653df888d0c39386a/312cc00672f6ea6a2091.json new file mode 100644 index 0000000000000000000000000000000000000000..e5a6dd504c79134017cdd3c506819dd63bd7a884 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9f58df9cfff5526c47d9483ba90a26f5535cb01f04c479e653df888d0c39386a/312cc00672f6ea6a2091.json @@ -0,0 +1,48 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "multiple-choice", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_num_choices": 4, + "static_sequence_length": 128, + "task": "multiple-choice", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9f58df9cfff5526c47d9483ba90a26f5535cb01f04c479e653df888d0c39386a/5bd82a6b5eab0494286d.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9f58df9cfff5526c47d9483ba90a26f5535cb01f04c479e653df888d0c39386a/5bd82a6b5eab0494286d.json new file mode 100644 index 0000000000000000000000000000000000000000..c36b5bc585f7640eec839a1f5dcb5234b69d70bf --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9f58df9cfff5526c47d9483ba90a26f5535cb01f04c479e653df888d0c39386a/5bd82a6b5eab0494286d.json @@ -0,0 +1,48 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "multiple-choice", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_num_choices": 4, + "static_sequence_length": 128, + "task": "multiple-choice", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9f8c560856ef5a5484fbcd7e637c5d569b6f1fc719a37e9c4de817843e7af814/1a5a3fbb3fbe346f29ed.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9f8c560856ef5a5484fbcd7e637c5d569b6f1fc719a37e9c4de817843e7af814/1a5a3fbb3fbe346f29ed.json new file mode 100644 index 0000000000000000000000000000000000000000..7edc09d4ebbfe6623f140bf4bd4576410963aada --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9f8c560856ef5a5484fbcd7e637c5d569b6f1fc719a37e9c4de817843e7af814/1a5a3fbb3fbe346f29ed.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-YolosModel", + "_task": "object-detection", + "architectures": [ + "YolosModel" + ], + "attention_probs_dropout_prob": 0.1, + "auxiliary_loss": false, + "bbox_cost": 5, + "bbox_loss_coefficient": 5, + "class_cost": 1, + "dtype": "float32", + "eos_coefficient": 0.1, + "giou_cost": 2, + "giou_loss_coefficient": 2, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1", + "2": "LABEL_2" + }, + "image_size": [ + 30, + 30 + ], + "initializer_range": 0.02, + "intermediate_size": 37, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1, + "LABEL_2": 2 + }, + "layer_norm_eps": 1e-12, + "model_type": "yolos", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "yolos", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "task": "object-detection", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_channels": 3, + "num_detection_tokens": 10, + "num_hidden_layers": 5, + "patch_size": 2, + "qkv_bias": true, + "use_mid_position_embeddings": true +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9f8c560856ef5a5484fbcd7e637c5d569b6f1fc719a37e9c4de817843e7af814/c82e0d8cda357ed4280f.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9f8c560856ef5a5484fbcd7e637c5d569b6f1fc719a37e9c4de817843e7af814/c82e0d8cda357ed4280f.json new file mode 100644 index 0000000000000000000000000000000000000000..02459a74ffb9270ee7715f7b2283bed18dc33a8b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/9f8c560856ef5a5484fbcd7e637c5d569b6f1fc719a37e9c4de817843e7af814/c82e0d8cda357ed4280f.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-YolosModel", + "_task": "object-detection", + "architectures": [ + "YolosModel" + ], + "attention_probs_dropout_prob": 0.1, + "auxiliary_loss": false, + "bbox_cost": 5, + "bbox_loss_coefficient": 5, + "class_cost": 1, + "dtype": "float32", + "eos_coefficient": 0.1, + "giou_cost": 2, + "giou_loss_coefficient": 2, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1", + "2": "LABEL_2" + }, + "image_size": [ + 30, + 30 + ], + "initializer_range": 0.02, + "intermediate_size": 37, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1, + "LABEL_2": 2 + }, + "layer_norm_eps": 1e-12, + "model_type": "yolos", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "yolos", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "task": "object-detection", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_channels": 3, + "num_detection_tokens": 10, + "num_hidden_layers": 5, + "patch_size": 2, + "qkv_bias": true, + "use_mid_position_embeddings": true +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/a25ff205155712c11f1104717823ef9e5c779d9bb77f36390863462b4ea9a165/8f31dad0c052fb818655.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/a25ff205155712c11f1104717823ef9e5c779d9bb77f36390863462b4ea9a165/8f31dad0c052fb818655.json new file mode 100644 index 0000000000000000000000000000000000000000..ea0824af642d3d9e9de067c699e16a065bc81d8a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/a25ff205155712c11f1104717823ef9e5c779d9bb77f36390863462b4ea9a165/8f31dad0c052fb818655.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RobertaModel", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "RobertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1024 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/a60a1b7e10f9ef562cab0966bdc6aecb8746b93e250ab9a2d8795a9eb936193a/8a49644de25851aebdb4.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/a60a1b7e10f9ef562cab0966bdc6aecb8746b93e250ab9a2d8795a9eb936193a/8a49644de25851aebdb4.json new file mode 100644 index 0000000000000000000000000000000000000000..760ec4c38f93310b9f9582a4bf07abeafe7bbd29 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/a60a1b7e10f9ef562cab0966bdc6aecb8746b93e250ab9a2d8795a9eb936193a/8a49644de25851aebdb4.json @@ -0,0 +1,45 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-vit", + "_task": "image-classification", + "architectures": [ + "ViTForImageClassification" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "encoder_stride": 16, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "image_size": 30, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "model_type": "vit", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "vit", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "task": "image-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_channels": 3, + "num_hidden_layers": 5, + "patch_size": 2, + "pooler_act": "tanh", + "pooler_output_size": 32, + "qkv_bias": true, + "vocab_size": {} +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/a60a1b7e10f9ef562cab0966bdc6aecb8746b93e250ab9a2d8795a9eb936193a/c46019d4d1ceee4d1b9f.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/a60a1b7e10f9ef562cab0966bdc6aecb8746b93e250ab9a2d8795a9eb936193a/c46019d4d1ceee4d1b9f.json new file mode 100644 index 0000000000000000000000000000000000000000..461c860907be0022135797a804a060f0983fc136 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/a60a1b7e10f9ef562cab0966bdc6aecb8746b93e250ab9a2d8795a9eb936193a/c46019d4d1ceee4d1b9f.json @@ -0,0 +1,45 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-vit", + "_task": "image-classification", + "architectures": [ + "ViTForImageClassification" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "encoder_stride": 16, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "image_size": 30, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "model_type": "vit", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "vit", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "task": "image-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_channels": 3, + "num_hidden_layers": 5, + "patch_size": 2, + "pooler_act": "tanh", + "pooler_output_size": 32, + "qkv_bias": true, + "vocab_size": {} +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ab9757663f9398391e7c111769816a7405defd6bf483bb319a112f748b32879c/a86ba94b3903ec685a95.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ab9757663f9398391e7c111769816a7405defd6bf483bb319a112f748b32879c/a86ba94b3903ec685a95.json new file mode 100644 index 0000000000000000000000000000000000000000..01f20a789a70131fdc28dc7b16064ecbdba45d7f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ab9757663f9398391e7c111769816a7405defd6bf483bb319a112f748b32879c/a86ba94b3903ec685a95.json @@ -0,0 +1,41 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MPNetModel", + "_task": "token-classification", + "architectures": [ + "MPNetModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 64, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mpnet", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mpnet", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "relative_attention_num_buckets": 32, + "vocab_size": 1125 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ad034600f6076b23aab8d1c574fbd4615ece3896625c462750f78fb74e9a5b20/1847045adee5dca6c7a9.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ad034600f6076b23aab8d1c574fbd4615ece3896625c462750f78fb74e9a5b20/1847045adee5dca6c7a9.json new file mode 100644 index 0000000000000000000000000000000000000000..0062b51fb56d6899bff767a7d9280f9d5bf289b7 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ad034600f6076b23aab8d1c574fbd4615ece3896625c462750f78fb74e9a5b20/1847045adee5dca6c7a9.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MobileBertModel", + "_task": "fill-mask", + "architectures": [ + "MobileBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_activation": true, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 37, + "intra_bottleneck_size": 128, + "key_query_shared_bottleneck": true, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mobilebert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mobilebert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "normalization_type": "no_norm", + "num_attention_heads": 4, + "num_feedforward_networks": 4, + "num_hidden_layers": 5, + "trigram_input": true, + "true_hidden_size": 128, + "type_vocab_size": 16, + "use_bottleneck": true, + "use_bottleneck_attention": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ae8001415c1a66de2bb2acd76e0c09bcdee6272638d00fe749684771f1569d3e/9e3994a9e7639c444c34.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ae8001415c1a66de2bb2acd76e0c09bcdee6272638d00fe749684771f1569d3e/9e3994a9e7639c444c34.json new file mode 100644 index 0000000000000000000000000000000000000000..e42f6373ac3ad2d905053681292802cfd559e067 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ae8001415c1a66de2bb2acd76e0c09bcdee6272638d00fe749684771f1569d3e/9e3994a9e7639c444c34.json @@ -0,0 +1,46 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ConvBertModel", + "_task": "feature-extraction", + "architectures": [ + "ConvBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "conv_kernel_size": 9, + "dtype": "float32", + "embedding_size": 768, + "head_ratio": 2, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "convbert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "convbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_groups": 1, + "num_hidden_layers": 5, + "type_vocab_size": 16, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/af54645e006da280cc1c55412e5667eb0f510e714835bd5f5423a39099d24ff0/5826c569eb88fbc0ee9d.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/af54645e006da280cc1c55412e5667eb0f510e714835bd5f5423a39099d24ff0/5826c569eb88fbc0ee9d.json new file mode 100644 index 0000000000000000000000000000000000000000..76c975bae5a1e43393129c4cbf80d14b5d6aa75f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/af54645e006da280cc1c55412e5667eb0f510e714835bd5f5423a39099d24ff0/5826c569eb88fbc0ee9d.json @@ -0,0 +1,49 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ElectraModel", + "_task": "fill-mask", + "architectures": [ + "ElectraModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "electra", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "electra", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "summary_activation": "gelu", + "summary_last_dropout": 0.1, + "summary_type": "first", + "summary_use_proj": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/af5e5522a0342bb7d1fcd43da2671a9679f4f5014fead5e39500f9afb6bb03f0/c29b0f31cb586add1f8e.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/af5e5522a0342bb7d1fcd43da2671a9679f4f5014fead5e39500f9afb6bb03f0/c29b0f31cb586add1f8e.json new file mode 100644 index 0000000000000000000000000000000000000000..cc2c37d4ed09d94b699e22b7d8ae73f080155353 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/af5e5522a0342bb7d1fcd43da2671a9679f4f5014fead5e39500f9afb6bb03f0/c29b0f31cb586add1f8e.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "feature-extraction", + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/albert/hf-internal-testing/tiny-random-AlbertModel/94661956f819d157a15d.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/albert/hf-internal-testing/tiny-random-AlbertModel/94661956f819d157a15d.json new file mode 100644 index 0000000000000000000000000000000000000000..4311c2c1f76655ad15281a2070f0bb4720784f88 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/albert/hf-internal-testing/tiny-random-AlbertModel/94661956f819d157a15d.json @@ -0,0 +1,46 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "feature-extraction", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b01158808fb39ea5dfba52e9e4c82781c3f4959bab6162229fd55fd0eba6eba9/00292c4574b468ed77be.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b01158808fb39ea5dfba52e9e4c82781c3f4959bab6162229fd55fd0eba6eba9/00292c4574b468ed77be.json new file mode 100644 index 0000000000000000000000000000000000000000..f12b68762afbff807782691b458737500e8eb202 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b01158808fb39ea5dfba52e9e4c82781c3f4959bab6162229fd55fd0eba6eba9/00292c4574b468ed77be.json @@ -0,0 +1,48 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-camembert", + "_task": "fill-mask", + "add_cross_attention": false, + "architectures": [ + "CamembertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "camembert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "camembert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b01158808fb39ea5dfba52e9e4c82781c3f4959bab6162229fd55fd0eba6eba9/4f29f0ba41748d2a1487.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b01158808fb39ea5dfba52e9e4c82781c3f4959bab6162229fd55fd0eba6eba9/4f29f0ba41748d2a1487.json new file mode 100644 index 0000000000000000000000000000000000000000..9d2c1bc3b59c6b240e9c19972e1b5c1344e961bf --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b01158808fb39ea5dfba52e9e4c82781c3f4959bab6162229fd55fd0eba6eba9/4f29f0ba41748d2a1487.json @@ -0,0 +1,48 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-camembert", + "_task": "fill-mask", + "add_cross_attention": false, + "architectures": [ + "CamembertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "camembert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "camembert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b125a7b377609804a31c59fe098482702740c1c8b1e999872e49cda0840be873/af083f76d4af65c09e37.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b125a7b377609804a31c59fe098482702740c1c8b1e999872e49cda0840be873/af083f76d4af65c09e37.json new file mode 100644 index 0000000000000000000000000000000000000000..11aeece6178d8fcdbfac4e27b38519676306b0c0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b125a7b377609804a31c59fe098482702740c1c8b1e999872e49cda0840be873/af083f76d4af65c09e37.json @@ -0,0 +1,48 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-camembert", + "_task": "token-classification", + "add_cross_attention": false, + "architectures": [ + "CamembertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "camembert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "camembert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b191d607e94819566800de30939d6c26cefbebc52bef9ff571aa1855a9ca0a4e/5df183a9a537186b793f.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b191d607e94819566800de30939d6c26cefbebc52bef9ff571aa1855a9ca0a4e/5df183a9a537186b793f.json new file mode 100644 index 0000000000000000000000000000000000000000..d7de9bfb131f7d639bd4eeecedd4efc1ecf982fa --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b191d607e94819566800de30939d6c26cefbebc52bef9ff571aa1855a9ca0a4e/5df183a9a537186b793f.json @@ -0,0 +1,169 @@ +{ + "_entry_class": "MultiModelCacheEntry", + "_model_id": "/home/tengomucho/.cache/huggingface/hub/models--echarlaix--tiny-random-stable-diffusion-xl/snapshots/434a0025554940d46ddd5dd10f0abc2788076b47/vae", + "_task": null, + "text_encoder": { + "architectures": [ + "CLIPTextModel" + ], + "attention_dropout": 0.0, + "dtype": "float32", + "export_model_type": "clip-text-model", + "hidden_act": "gelu", + "hidden_size": 32, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 77, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "output_hidden_states": true, + "vocab_size": 1000 + }, + "text_encoder_2": { + "architectures": [ + "CLIPTextModelWithProjection" + ], + "attention_dropout": 0.0, + "dtype": "float32", + "export_model_type": "clip-text-with-projection", + "hidden_act": "gelu", + "hidden_size": 32, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 77, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "output_hidden_states": true, + "vocab_size": 1000 + }, + "unet": { + "_class_name": "UNet2DConditionModel", + "act_fn": "silu", + "addition_embed_type": "text_time", + "addition_embed_type_num_heads": 64, + "addition_time_embed_dim": 8, + "attention_head_dim": [ + 2, + 4 + ], + "attention_type": "default", + "block_out_channels": [ + 32, + 64 + ], + "center_input_sample": false, + "class_embed_type": null, + "class_embeddings_concat": false, + "conv_in_kernel": 3, + "conv_out_kernel": 3, + "cross_attention_dim": 64, + "cross_attention_norm": null, + "down_block_types": [ + "DownBlock2D", + "CrossAttnDownBlock2D" + ], + "downsample_padding": 1, + "dropout": 0.0, + "dual_cross_attention": false, + "encoder_hid_dim": null, + "encoder_hid_dim_type": null, + "flip_sin_to_cos": true, + "freq_shift": 0, + "in_channels": 4, + "layers_per_block": 2, + "mid_block_only_cross_attention": null, + "mid_block_scale_factor": 1, + "mid_block_type": "UNetMidBlock2DCrossAttn", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 32, + "static_num_channels": 4, + "static_sequence_length": 77, + "static_vae_scale_factor": 2, + "static_width": 32, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_eps": 1e-05, + "norm_num_groups": 32, + "num_attention_heads": null, + "num_class_embeds": null, + "only_cross_attention": false, + "out_channels": 4, + "output_attentions": false, + "projection_class_embeddings_input_dim": 80, + "resnet_out_scale_factor": 1.0, + "resnet_skip_time_act": false, + "resnet_time_scale_shift": "default", + "reverse_transformer_layers_per_block": null, + "time_cond_proj_dim": null, + "time_embedding_act_fn": null, + "time_embedding_dim": null, + "time_embedding_type": "positional", + "timestep_post_act": null, + "transformer_layers_per_block": [ + 1, + 2 + ], + "up_block_types": [ + "CrossAttnUpBlock2D", + "UpBlock2D" + ], + "upcast_attention": false, + "use_linear_projection": true + } +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b191d607e94819566800de30939d6c26cefbebc52bef9ff571aa1855a9ca0a4e/73e765061ca0edc0984c.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b191d607e94819566800de30939d6c26cefbebc52bef9ff571aa1855a9ca0a4e/73e765061ca0edc0984c.json new file mode 100644 index 0000000000000000000000000000000000000000..e5859016e4b38f0b12a1275a687e2b96b7768d45 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b191d607e94819566800de30939d6c26cefbebc52bef9ff571aa1855a9ca0a4e/73e765061ca0edc0984c.json @@ -0,0 +1,125 @@ +{ + "_entry_class": "MultiModelCacheEntry", + "_model_id": "/home/tengomucho/.cache/huggingface/hub/models--hf-internal-testing--tiny-stable-diffusion-torch/snapshots/a88cdfbd91f96ec7f61eb7484b652ff0f4ee701d/vae", + "_task": null, + "text_encoder": { + "architectures": [ + "CLIPTextModel" + ], + "attention_dropout": 0.0, + "dropout": 0.0, + "dtype": "float32", + "export_model_type": "clip-text-model", + "hidden_act": "quick_gelu", + "hidden_size": 32, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 77, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "vocab_size": 1000 + }, + "unet": { + "_class_name": "UNet2DConditionModel", + "act_fn": "silu", + "addition_embed_type": null, + "addition_embed_type_num_heads": 64, + "addition_time_embed_dim": null, + "attention_head_dim": 8, + "attention_type": "default", + "block_out_channels": [ + 32, + 64 + ], + "center_input_sample": false, + "class_embed_type": null, + "class_embeddings_concat": false, + "conv_in_kernel": 3, + "conv_out_kernel": 3, + "cross_attention_dim": 32, + "cross_attention_norm": null, + "down_block_types": [ + "DownBlock2D", + "CrossAttnDownBlock2D" + ], + "downsample_padding": 1, + "dropout": 0.0, + "dual_cross_attention": false, + "encoder_hid_dim": null, + "encoder_hid_dim_type": null, + "flip_sin_to_cos": true, + "freq_shift": 0, + "in_channels": 4, + "layers_per_block": 2, + "mid_block_only_cross_attention": null, + "mid_block_scale_factor": 1, + "mid_block_type": "UNetMidBlock2DCrossAttn", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 32, + "static_num_channels": 4, + "static_sequence_length": 77, + "static_vae_scale_factor": 2, + "static_width": 32, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_eps": 1e-05, + "norm_num_groups": 32, + "num_attention_heads": null, + "num_class_embeds": null, + "only_cross_attention": false, + "out_channels": 4, + "output_attentions": false, + "projection_class_embeddings_input_dim": null, + "resnet_out_scale_factor": 1.0, + "resnet_skip_time_act": false, + "resnet_time_scale_shift": "default", + "reverse_transformer_layers_per_block": null, + "time_cond_proj_dim": null, + "time_embedding_act_fn": null, + "time_embedding_dim": null, + "time_embedding_type": "positional", + "timestep_post_act": null, + "transformer_layers_per_block": 1, + "up_block_types": [ + "CrossAttnUpBlock2D", + "UpBlock2D" + ], + "upcast_attention": false, + "use_linear_projection": false + } +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b191d607e94819566800de30939d6c26cefbebc52bef9ff571aa1855a9ca0a4e/c6310bffbfbf29e5d927.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b191d607e94819566800de30939d6c26cefbebc52bef9ff571aa1855a9ca0a4e/c6310bffbfbf29e5d927.json new file mode 100644 index 0000000000000000000000000000000000000000..cbaa15b7bf6770f9cfcece82af47da9bf448077b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b191d607e94819566800de30939d6c26cefbebc52bef9ff571aa1855a9ca0a4e/c6310bffbfbf29e5d927.json @@ -0,0 +1,124 @@ +{ + "_entry_class": "MultiModelCacheEntry", + "_model_id": "/home/tengomucho/.cache/huggingface/hub/models--echarlaix--tiny-random-latent-consistency/snapshots/ea16e1fcf89fe667eef6639bfd14ac8701bff7b9/vae", + "_task": null, + "text_encoder": { + "architectures": [ + "CLIPTextModel" + ], + "attention_dropout": 0.0, + "dtype": "float32", + "export_model_type": "clip-text-model", + "hidden_act": "quick_gelu", + "hidden_size": 32, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 64, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 77, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 8, + "num_hidden_layers": 3, + "vocab_size": 1000 + }, + "unet": { + "_class_name": "UNet2DConditionModel", + "act_fn": "silu", + "addition_embed_type": null, + "addition_embed_type_num_heads": 64, + "addition_time_embed_dim": null, + "attention_head_dim": 8, + "attention_type": "default", + "block_out_channels": [ + 4, + 8 + ], + "center_input_sample": false, + "class_embed_type": null, + "class_embeddings_concat": false, + "conv_in_kernel": 3, + "conv_out_kernel": 3, + "cross_attention_dim": 32, + "cross_attention_norm": null, + "down_block_types": [ + "DownBlock2D", + "CrossAttnDownBlock2D" + ], + "downsample_padding": 1, + "dropout": 0.0, + "dual_cross_attention": false, + "encoder_hid_dim": null, + "encoder_hid_dim_type": null, + "flip_sin_to_cos": true, + "freq_shift": 0, + "in_channels": 4, + "layers_per_block": 1, + "mid_block_only_cross_attention": null, + "mid_block_scale_factor": 1, + "mid_block_type": "UNetMidBlock2DCrossAttn", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 32, + "static_num_channels": 4, + "static_sequence_length": 77, + "static_vae_scale_factor": 2, + "static_width": 32, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_eps": 1e-05, + "norm_num_groups": 2, + "num_attention_heads": null, + "num_class_embeds": null, + "only_cross_attention": false, + "out_channels": 4, + "output_attentions": false, + "projection_class_embeddings_input_dim": null, + "resnet_out_scale_factor": 1.0, + "resnet_skip_time_act": false, + "resnet_time_scale_shift": "default", + "reverse_transformer_layers_per_block": null, + "time_cond_proj_dim": 32, + "time_embedding_act_fn": null, + "time_embedding_dim": null, + "time_embedding_type": "positional", + "timestep_post_act": null, + "transformer_layers_per_block": 1, + "up_block_types": [ + "CrossAttnUpBlock2D", + "UpBlock2D" + ], + "upcast_attention": false, + "use_linear_projection": false + } +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b1c79ee792bcc8cabcf195cfbaa45e0f60149b9911eaba89d5f2b421b93fd8c8/e1adfa2a55ce204ba39b.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b1c79ee792bcc8cabcf195cfbaa45e0f60149b9911eaba89d5f2b421b93fd8c8/e1adfa2a55ce204ba39b.json new file mode 100644 index 0000000000000000000000000000000000000000..d4f655f55b5040c83df86096bef3feb08936bd2c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b1c79ee792bcc8cabcf195cfbaa45e0f60149b9911eaba89d5f2b421b93fd8c8/e1adfa2a55ce204ba39b.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RobertaModel", + "_task": "fill-mask", + "architectures": [ + "RobertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1024 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b32e36204985263b8a72b4efaaeeb64dfe3ed4019e2361a28ae97691cd185f06/c33ee1c0b1397f908a2c.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b32e36204985263b8a72b4efaaeeb64dfe3ed4019e2361a28ae97691cd185f06/c33ee1c0b1397f908a2c.json new file mode 100644 index 0000000000000000000000000000000000000000..bd811c631699cde9202dcc17bf8f26253451afcd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b32e36204985263b8a72b4efaaeeb64dfe3ed4019e2361a28ae97691cd185f06/c33ee1c0b1397f908a2c.json @@ -0,0 +1,56 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-xlm-roberta", + "_task": "fill-mask", + "add_cross_attention": false, + "architectures": [ + "XLMRobertaForCausalLM" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "d_ff": 256, + "d_kv": 8, + "d_model": 64, + "dtype": "float32", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 256, + "initializer_range": 0.02, + "intermediate_size": 256, + "is_decoder": false, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 64, + "model_type": "xlm-roberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "xlm-roberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 2, + "num_decoder_layers": 2, + "num_heads": 2, + "num_hidden_layers": 2, + "num_layers": 2, + "output_past": true, + "position_embedding_type": "absolute", + "relative_attention_num_buckets": 32, + "tie_word_embeddings": true, + "type_vocab_size": 1, + "use_cache": true, + "vocab_size": 5002 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b499e2169427d86cfd5ea5795ff78579888b6c637e9f7ad212c17b21cd86a3cd/497f7d7dac691afa40a2.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b499e2169427d86cfd5ea5795ff78579888b6c637e9f7ad212c17b21cd86a3cd/497f7d7dac691afa40a2.json new file mode 100644 index 0000000000000000000000000000000000000000..12a8aea2736f18cbc25ad585944936af7232af08 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b499e2169427d86cfd5ea5795ff78579888b6c637e9f7ad212c17b21cd86a3cd/497f7d7dac691afa40a2.json @@ -0,0 +1,2068 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-mobilevit", + "_task": "semantic-segmentation", + "architectures": [ + "MobileViTForImageClassification" + ], + "aspp_dropout_prob": 0.1, + "aspp_out_channels": 256, + "atrous_rates": [ + 6, + 12, + 18 + ], + "attention_probs_dropout_prob": 0.0, + "classifier_dropout_prob": 0.1, + "conv_kernel_size": 3, + "dtype": "float32", + "expand_ratio": 4.0, + "hidden_act": "silu", + "hidden_dropout_prob": 0.1, + "hidden_sizes": [ + 6, + 12, + 24 + ], + "id2label": { + "0": "tench, Tinca tinca", + "1": "goldfish, Carassius auratus", + "2": "great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias", + "3": "tiger shark, Galeocerdo cuvieri", + "4": "hammerhead, hammerhead shark", + "5": "electric ray, crampfish, numbfish, torpedo", + "6": "stingray", + "7": "cock", + "8": "hen", + "9": "ostrich, Struthio camelus", + "10": "brambling, Fringilla montifringilla", + "11": "goldfinch, Carduelis carduelis", + "12": "house finch, linnet, Carpodacus mexicanus", + "13": "junco, snowbird", + "14": "indigo bunting, indigo finch, indigo bird, Passerina cyanea", + "15": "robin, American robin, Turdus migratorius", + "16": "bulbul", + "17": "jay", + "18": "magpie", + "19": "chickadee", + "20": "water ouzel, dipper", + "21": "kite", + "22": "bald eagle, American eagle, Haliaeetus leucocephalus", + "23": "vulture", + "24": "great grey owl, great gray owl, Strix nebulosa", + "25": "European fire salamander, Salamandra salamandra", + "26": "common newt, Triturus vulgaris", + "27": "eft", + "28": "spotted salamander, Ambystoma maculatum", + "29": "axolotl, mud puppy, Ambystoma mexicanum", + "30": "bullfrog, Rana catesbeiana", + "31": "tree frog, tree-frog", + "32": "tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui", + "33": "loggerhead, loggerhead turtle, Caretta caretta", + "34": "leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea", + "35": "mud turtle", + "36": "terrapin", + "37": "box turtle, box tortoise", + "38": "banded gecko", + "39": "common iguana, iguana, Iguana iguana", + "40": "American chameleon, anole, Anolis carolinensis", + "41": "whiptail, whiptail lizard", + "42": "agama", + "43": "frilled lizard, Chlamydosaurus kingi", + "44": "alligator lizard", + "45": "Gila monster, Heloderma suspectum", + "46": "green lizard, Lacerta viridis", + "47": "African chameleon, Chamaeleo chamaeleon", + "48": "Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis", + "49": "African crocodile, Nile crocodile, Crocodylus niloticus", + "50": "American alligator, Alligator mississipiensis", + "51": "triceratops", + "52": "thunder snake, worm snake, Carphophis amoenus", + "53": "ringneck snake, ring-necked snake, ring snake", + "54": "hognose snake, puff adder, sand viper", + "55": "green snake, grass snake", + "56": "king snake, kingsnake", + "57": "garter snake, grass snake", + "58": "water snake", + "59": "vine snake", + "60": "night snake, Hypsiglena torquata", + "61": "boa constrictor, Constrictor constrictor", + "62": "rock python, rock snake, Python sebae", + "63": "Indian cobra, Naja naja", + "64": "green mamba", + "65": "sea snake", + "66": "horned viper, cerastes, sand viper, horned asp, Cerastes cornutus", + "67": "diamondback, diamondback rattlesnake, Crotalus adamanteus", + "68": "sidewinder, horned rattlesnake, Crotalus cerastes", + "69": "trilobite", + "70": "harvestman, daddy longlegs, Phalangium opilio", + "71": "scorpion", + "72": "black and gold garden spider, Argiope aurantia", + "73": "barn spider, Araneus cavaticus", + "74": "garden spider, Aranea diademata", + "75": "black widow, Latrodectus mactans", + "76": "tarantula", + "77": "wolf spider, hunting spider", + "78": "tick", + "79": "centipede", + "80": "black grouse", + "81": "ptarmigan", + "82": "ruffed grouse, partridge, Bonasa umbellus", + "83": "prairie chicken, prairie grouse, prairie fowl", + "84": "peacock", + "85": "quail", + "86": "partridge", + "87": "African grey, African gray, Psittacus erithacus", + "88": "macaw", + "89": "sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita", + "90": "lorikeet", + "91": "coucal", + "92": "bee eater", + "93": "hornbill", + "94": "hummingbird", + "95": "jacamar", + "96": "toucan", + "97": "drake", + "98": "red-breasted merganser, Mergus serrator", + "99": "goose", + "100": "black swan, Cygnus atratus", + "101": "tusker", + "102": "echidna, spiny anteater, anteater", + "103": "platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus", + "104": "wallaby, brush kangaroo", + "105": "koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus", + "106": "wombat", + "107": "jellyfish", + "108": "sea anemone, anemone", + "109": "brain coral", + "110": "flatworm, platyhelminth", + "111": "nematode, nematode worm, roundworm", + "112": "conch", + "113": "snail", + "114": "slug", + "115": "sea slug, nudibranch", + "116": "chiton, coat-of-mail shell, sea cradle, polyplacophore", + "117": "chambered nautilus, pearly nautilus, nautilus", + "118": "Dungeness crab, Cancer magister", + "119": "rock crab, Cancer irroratus", + "120": "fiddler crab", + "121": "king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica", + "122": "American lobster, Northern lobster, Maine lobster, Homarus americanus", + "123": "spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish", + "124": "crayfish, crawfish, crawdad, crawdaddy", + "125": "hermit crab", + "126": "isopod", + "127": "white stork, Ciconia ciconia", + "128": "black stork, Ciconia nigra", + "129": "spoonbill", + "130": "flamingo", + "131": "little blue heron, Egretta caerulea", + "132": "American egret, great white heron, Egretta albus", + "133": "bittern", + "134": "crane", + "135": "limpkin, Aramus pictus", + "136": "European gallinule, Porphyrio porphyrio", + "137": "American coot, marsh hen, mud hen, water hen, Fulica americana", + "138": "bustard", + "139": "ruddy turnstone, Arenaria interpres", + "140": "red-backed sandpiper, dunlin, Erolia alpina", + "141": "redshank, Tringa totanus", + "142": "dowitcher", + "143": "oystercatcher, oyster catcher", + "144": "pelican", + "145": "king penguin, Aptenodytes patagonica", + "146": "albatross, mollymawk", + "147": "grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus", + "148": "killer whale, killer, orca, grampus, sea wolf, Orcinus orca", + "149": "dugong, Dugong dugon", + "150": "sea lion", + "151": "Chihuahua", + "152": "Japanese spaniel", + "153": "Maltese dog, Maltese terrier, Maltese", + "154": "Pekinese, Pekingese, Peke", + "155": "Shih-Tzu", + "156": "Blenheim spaniel", + "157": "papillon", + "158": "toy terrier", + "159": "Rhodesian ridgeback", + "160": "Afghan hound, Afghan", + "161": "basset, basset hound", + "162": "beagle", + "163": "bloodhound, sleuthhound", + "164": "bluetick", + "165": "black-and-tan coonhound", + "166": "Walker hound, Walker foxhound", + "167": "English foxhound", + "168": "redbone", + "169": "borzoi, Russian wolfhound", + "170": "Irish wolfhound", + "171": "Italian greyhound", + "172": "whippet", + "173": "Ibizan hound, Ibizan Podenco", + "174": "Norwegian elkhound, elkhound", + "175": "otterhound, otter hound", + "176": "Saluki, gazelle hound", + "177": "Scottish deerhound, deerhound", + "178": "Weimaraner", + "179": "Staffordshire bullterrier, Staffordshire bull terrier", + "180": "American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier", + "181": "Bedlington terrier", + "182": "Border terrier", + "183": "Kerry blue terrier", + "184": "Irish terrier", + "185": "Norfolk terrier", + "186": "Norwich terrier", + "187": "Yorkshire terrier", + "188": "wire-haired fox terrier", + "189": "Lakeland terrier", + "190": "Sealyham terrier, Sealyham", + "191": "Airedale, Airedale terrier", + "192": "cairn, cairn terrier", + "193": "Australian terrier", + "194": "Dandie Dinmont, Dandie Dinmont terrier", + "195": "Boston bull, Boston terrier", + "196": "miniature schnauzer", + "197": "giant schnauzer", + "198": "standard schnauzer", + "199": "Scotch terrier, Scottish terrier, Scottie", + "200": "Tibetan terrier, chrysanthemum dog", + "201": "silky terrier, Sydney silky", + "202": "soft-coated wheaten terrier", + "203": "West Highland white terrier", + "204": "Lhasa, Lhasa apso", + "205": "flat-coated retriever", + "206": "curly-coated retriever", + "207": "golden retriever", + "208": "Labrador retriever", + "209": "Chesapeake Bay retriever", + "210": "German short-haired pointer", + "211": "vizsla, Hungarian pointer", + "212": "English setter", + "213": "Irish setter, red setter", + "214": "Gordon setter", + "215": "Brittany spaniel", + "216": "clumber, clumber spaniel", + "217": "English springer, English springer spaniel", + "218": "Welsh springer spaniel", + "219": "cocker spaniel, English cocker spaniel, cocker", + "220": "Sussex spaniel", + "221": "Irish water spaniel", + "222": "kuvasz", + "223": "schipperke", + "224": "groenendael", + "225": "malinois", + "226": "briard", + "227": "kelpie", + "228": "komondor", + "229": "Old English sheepdog, bobtail", + "230": "Shetland sheepdog, Shetland sheep dog, Shetland", + "231": "collie", + "232": "Border collie", + "233": "Bouvier des Flandres, Bouviers des Flandres", + "234": "Rottweiler", + "235": "German shepherd, German shepherd dog, German police dog, alsatian", + "236": "Doberman, Doberman pinscher", + "237": "miniature pinscher", + "238": "Greater Swiss Mountain dog", + "239": "Bernese mountain dog", + "240": "Appenzeller", + "241": "EntleBucher", + "242": "boxer", + "243": "bull mastiff", + "244": "Tibetan mastiff", + "245": "French bulldog", + "246": "Great Dane", + "247": "Saint Bernard, St Bernard", + "248": "Eskimo dog, husky", + "249": "malamute, malemute, Alaskan malamute", + "250": "Siberian husky", + "251": "dalmatian, coach dog, carriage dog", + "252": "affenpinscher, monkey pinscher, monkey dog", + "253": "basenji", + "254": "pug, pug-dog", + "255": "Leonberg", + "256": "Newfoundland, Newfoundland dog", + "257": "Great Pyrenees", + "258": "Samoyed, Samoyede", + "259": "Pomeranian", + "260": "chow, chow chow", + "261": "keeshond", + "262": "Brabancon griffon", + "263": "Pembroke, Pembroke Welsh corgi", + "264": "Cardigan, Cardigan Welsh corgi", + "265": "toy poodle", + "266": "miniature poodle", + "267": "standard poodle", + "268": "Mexican hairless", + "269": "timber wolf, grey wolf, gray wolf, Canis lupus", + "270": "white wolf, Arctic wolf, Canis lupus tundrarum", + "271": "red wolf, maned wolf, Canis rufus, Canis niger", + "272": "coyote, prairie wolf, brush wolf, Canis latrans", + "273": "dingo, warrigal, warragal, Canis dingo", + "274": "dhole, Cuon alpinus", + "275": "African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus", + "276": "hyena, hyaena", + "277": "red fox, Vulpes vulpes", + "278": "kit fox, Vulpes macrotis", + "279": "Arctic fox, white fox, Alopex lagopus", + "280": "grey fox, gray fox, Urocyon cinereoargenteus", + "281": "tabby, tabby cat", + "282": "tiger cat", + "283": "Persian cat", + "284": "Siamese cat, Siamese", + "285": "Egyptian cat", + "286": "cougar, puma, catamount, mountain lion, painter, panther, Felis concolor", + "287": "lynx, catamount", + "288": "leopard, Panthera pardus", + "289": "snow leopard, ounce, Panthera uncia", + "290": "jaguar, panther, Panthera onca, Felis onca", + "291": "lion, king of beasts, Panthera leo", + "292": "tiger, Panthera tigris", + "293": "cheetah, chetah, Acinonyx jubatus", + "294": "brown bear, bruin, Ursus arctos", + "295": "American black bear, black bear, Ursus americanus, Euarctos americanus", + "296": "ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus", + "297": "sloth bear, Melursus ursinus, Ursus ursinus", + "298": "mongoose", + "299": "meerkat, mierkat", + "300": "tiger beetle", + "301": "ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle", + "302": "ground beetle, carabid beetle", + "303": "long-horned beetle, longicorn, longicorn beetle", + "304": "leaf beetle, chrysomelid", + "305": "dung beetle", + "306": "rhinoceros beetle", + "307": "weevil", + "308": "fly", + "309": "bee", + "310": "ant, emmet, pismire", + "311": "grasshopper, hopper", + "312": "cricket", + "313": "walking stick, walkingstick, stick insect", + "314": "cockroach, roach", + "315": "mantis, mantid", + "316": "cicada, cicala", + "317": "leafhopper", + "318": "lacewing, lacewing fly", + "319": "dragonfly, darning needle, devil's darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk", + "320": "damselfly", + "321": "admiral", + "322": "ringlet, ringlet butterfly", + "323": "monarch, monarch butterfly, milkweed butterfly, Danaus plexippus", + "324": "cabbage butterfly", + "325": "sulphur butterfly, sulfur butterfly", + "326": "lycaenid, lycaenid butterfly", + "327": "starfish, sea star", + "328": "sea urchin", + "329": "sea cucumber, holothurian", + "330": "wood rabbit, cottontail, cottontail rabbit", + "331": "hare", + "332": "Angora, Angora rabbit", + "333": "hamster", + "334": "porcupine, hedgehog", + "335": "fox squirrel, eastern fox squirrel, Sciurus niger", + "336": "marmot", + "337": "beaver", + "338": "guinea pig, Cavia cobaya", + "339": "sorrel", + "340": "zebra", + "341": "hog, pig, grunter, squealer, Sus scrofa", + "342": "wild boar, boar, Sus scrofa", + "343": "warthog", + "344": "hippopotamus, hippo, river horse, Hippopotamus amphibius", + "345": "ox", + "346": "water buffalo, water ox, Asiatic buffalo, Bubalus bubalis", + "347": "bison", + "348": "ram, tup", + "349": "bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis", + "350": "ibex, Capra ibex", + "351": "hartebeest", + "352": "impala, Aepyceros melampus", + "353": "gazelle", + "354": "Arabian camel, dromedary, Camelus dromedarius", + "355": "llama", + "356": "weasel", + "357": "mink", + "358": "polecat, fitch, foulmart, foumart, Mustela putorius", + "359": "black-footed ferret, ferret, Mustela nigripes", + "360": "otter", + "361": "skunk, polecat, wood pussy", + "362": "badger", + "363": "armadillo", + "364": "three-toed sloth, ai, Bradypus tridactylus", + "365": "orangutan, orang, orangutang, Pongo pygmaeus", + "366": "gorilla, Gorilla gorilla", + "367": "chimpanzee, chimp, Pan troglodytes", + "368": "gibbon, Hylobates lar", + "369": "siamang, Hylobates syndactylus, Symphalangus syndactylus", + "370": "guenon, guenon monkey", + "371": "patas, hussar monkey, Erythrocebus patas", + "372": "baboon", + "373": "macaque", + "374": "langur", + "375": "colobus, colobus monkey", + "376": "proboscis monkey, Nasalis larvatus", + "377": "marmoset", + "378": "capuchin, ringtail, Cebus capucinus", + "379": "howler monkey, howler", + "380": "titi, titi monkey", + "381": "spider monkey, Ateles geoffroyi", + "382": "squirrel monkey, Saimiri sciureus", + "383": "Madagascar cat, ring-tailed lemur, Lemur catta", + "384": "indri, indris, Indri indri, Indri brevicaudatus", + "385": "Indian elephant, Elephas maximus", + "386": "African elephant, Loxodonta africana", + "387": "lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens", + "388": "giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca", + "389": "barracouta, snoek", + "390": "eel", + "391": "coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch", + "392": "rock beauty, Holocanthus tricolor", + "393": "anemone fish", + "394": "sturgeon", + "395": "gar, garfish, garpike, billfish, Lepisosteus osseus", + "396": "lionfish", + "397": "puffer, pufferfish, blowfish, globefish", + "398": "abacus", + "399": "abaya", + "400": "academic gown, academic robe, judge's robe", + "401": "accordion, piano accordion, squeeze box", + "402": "acoustic guitar", + "403": "aircraft carrier, carrier, flattop, attack aircraft carrier", + "404": "airliner", + "405": "airship, dirigible", + "406": "altar", + "407": "ambulance", + "408": "amphibian, amphibious vehicle", + "409": "analog clock", + "410": "apiary, bee house", + "411": "apron", + "412": "ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin", + "413": "assault rifle, assault gun", + "414": "backpack, back pack, knapsack, packsack, rucksack, haversack", + "415": "bakery, bakeshop, bakehouse", + "416": "balance beam, beam", + "417": "balloon", + "418": "ballpoint, ballpoint pen, ballpen, Biro", + "419": "Band Aid", + "420": "banjo", + "421": "bannister, banister, balustrade, balusters, handrail", + "422": "barbell", + "423": "barber chair", + "424": "barbershop", + "425": "barn", + "426": "barometer", + "427": "barrel, cask", + "428": "barrow, garden cart, lawn cart, wheelbarrow", + "429": "baseball", + "430": "basketball", + "431": "bassinet", + "432": "bassoon", + "433": "bathing cap, swimming cap", + "434": "bath towel", + "435": "bathtub, bathing tub, bath, tub", + "436": "beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon", + "437": "beacon, lighthouse, beacon light, pharos", + "438": "beaker", + "439": "bearskin, busby, shako", + "440": "beer bottle", + "441": "beer glass", + "442": "bell cote, bell cot", + "443": "bib", + "444": "bicycle-built-for-two, tandem bicycle, tandem", + "445": "bikini, two-piece", + "446": "binder, ring-binder", + "447": "binoculars, field glasses, opera glasses", + "448": "birdhouse", + "449": "boathouse", + "450": "bobsled, bobsleigh, bob", + "451": "bolo tie, bolo, bola tie, bola", + "452": "bonnet, poke bonnet", + "453": "bookcase", + "454": "bookshop, bookstore, bookstall", + "455": "bottlecap", + "456": "bow", + "457": "bow tie, bow-tie, bowtie", + "458": "brass, memorial tablet, plaque", + "459": "brassiere, bra, bandeau", + "460": "breakwater, groin, groyne, mole, bulwark, seawall, jetty", + "461": "breastplate, aegis, egis", + "462": "broom", + "463": "bucket, pail", + "464": "buckle", + "465": "bulletproof vest", + "466": "bullet train, bullet", + "467": "butcher shop, meat market", + "468": "cab, hack, taxi, taxicab", + "469": "caldron, cauldron", + "470": "candle, taper, wax light", + "471": "cannon", + "472": "canoe", + "473": "can opener, tin opener", + "474": "cardigan", + "475": "car mirror", + "476": "carousel, carrousel, merry-go-round, roundabout, whirligig", + "477": "carpenter's kit, tool kit", + "478": "carton", + "479": "car wheel", + "480": "cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM", + "481": "cassette", + "482": "cassette player", + "483": "castle", + "484": "catamaran", + "485": "CD player", + "486": "cello, violoncello", + "487": "cellular telephone, cellular phone, cellphone, cell, mobile phone", + "488": "chain", + "489": "chainlink fence", + "490": "chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour", + "491": "chain saw, chainsaw", + "492": "chest", + "493": "chiffonier, commode", + "494": "chime, bell, gong", + "495": "china cabinet, china closet", + "496": "Christmas stocking", + "497": "church, church building", + "498": "cinema, movie theater, movie theatre, movie house, picture palace", + "499": "cleaver, meat cleaver, chopper", + "500": "cliff dwelling", + "501": "cloak", + "502": "clog, geta, patten, sabot", + "503": "cocktail shaker", + "504": "coffee mug", + "505": "coffeepot", + "506": "coil, spiral, volute, whorl, helix", + "507": "combination lock", + "508": "computer keyboard, keypad", + "509": "confectionery, confectionary, candy store", + "510": "container ship, containership, container vessel", + "511": "convertible", + "512": "corkscrew, bottle screw", + "513": "cornet, horn, trumpet, trump", + "514": "cowboy boot", + "515": "cowboy hat, ten-gallon hat", + "516": "cradle", + "517": "crane", + "518": "crash helmet", + "519": "crate", + "520": "crib, cot", + "521": "Crock Pot", + "522": "croquet ball", + "523": "crutch", + "524": "cuirass", + "525": "dam, dike, dyke", + "526": "desk", + "527": "desktop computer", + "528": "dial telephone, dial phone", + "529": "diaper, nappy, napkin", + "530": "digital clock", + "531": "digital watch", + "532": "dining table, board", + "533": "dishrag, dishcloth", + "534": "dishwasher, dish washer, dishwashing machine", + "535": "disk brake, disc brake", + "536": "dock, dockage, docking facility", + "537": "dogsled, dog sled, dog sleigh", + "538": "dome", + "539": "doormat, welcome mat", + "540": "drilling platform, offshore rig", + "541": "drum, membranophone, tympan", + "542": "drumstick", + "543": "dumbbell", + "544": "Dutch oven", + "545": "electric fan, blower", + "546": "electric guitar", + "547": "electric locomotive", + "548": "entertainment center", + "549": "envelope", + "550": "espresso maker", + "551": "face powder", + "552": "feather boa, boa", + "553": "file, file cabinet, filing cabinet", + "554": "fireboat", + "555": "fire engine, fire truck", + "556": "fire screen, fireguard", + "557": "flagpole, flagstaff", + "558": "flute, transverse flute", + "559": "folding chair", + "560": "football helmet", + "561": "forklift", + "562": "fountain", + "563": "fountain pen", + "564": "four-poster", + "565": "freight car", + "566": "French horn, horn", + "567": "frying pan, frypan, skillet", + "568": "fur coat", + "569": "garbage truck, dustcart", + "570": "gasmask, respirator, gas helmet", + "571": "gas pump, gasoline pump, petrol pump, island dispenser", + "572": "goblet", + "573": "go-kart", + "574": "golf ball", + "575": "golfcart, golf cart", + "576": "gondola", + "577": "gong, tam-tam", + "578": "gown", + "579": "grand piano, grand", + "580": "greenhouse, nursery, glasshouse", + "581": "grille, radiator grille", + "582": "grocery store, grocery, food market, market", + "583": "guillotine", + "584": "hair slide", + "585": "hair spray", + "586": "half track", + "587": "hammer", + "588": "hamper", + "589": "hand blower, blow dryer, blow drier, hair dryer, hair drier", + "590": "hand-held computer, hand-held microcomputer", + "591": "handkerchief, hankie, hanky, hankey", + "592": "hard disc, hard disk, fixed disk", + "593": "harmonica, mouth organ, harp, mouth harp", + "594": "harp", + "595": "harvester, reaper", + "596": "hatchet", + "597": "holster", + "598": "home theater, home theatre", + "599": "honeycomb", + "600": "hook, claw", + "601": "hoopskirt, crinoline", + "602": "horizontal bar, high bar", + "603": "horse cart, horse-cart", + "604": "hourglass", + "605": "iPod", + "606": "iron, smoothing iron", + "607": "jack-o'-lantern", + "608": "jean, blue jean, denim", + "609": "jeep, landrover", + "610": "jersey, T-shirt, tee shirt", + "611": "jigsaw puzzle", + "612": "jinrikisha, ricksha, rickshaw", + "613": "joystick", + "614": "kimono", + "615": "knee pad", + "616": "knot", + "617": "lab coat, laboratory coat", + "618": "ladle", + "619": "lampshade, lamp shade", + "620": "laptop, laptop computer", + "621": "lawn mower, mower", + "622": "lens cap, lens cover", + "623": "letter opener, paper knife, paperknife", + "624": "library", + "625": "lifeboat", + "626": "lighter, light, igniter, ignitor", + "627": "limousine, limo", + "628": "liner, ocean liner", + "629": "lipstick, lip rouge", + "630": "Loafer", + "631": "lotion", + "632": "loudspeaker, speaker, speaker unit, loudspeaker system, speaker system", + "633": "loupe, jeweler's loupe", + "634": "lumbermill, sawmill", + "635": "magnetic compass", + "636": "mailbag, postbag", + "637": "mailbox, letter box", + "638": "maillot", + "639": "maillot, tank suit", + "640": "manhole cover", + "641": "maraca", + "642": "marimba, xylophone", + "643": "mask", + "644": "matchstick", + "645": "maypole", + "646": "maze, labyrinth", + "647": "measuring cup", + "648": "medicine chest, medicine cabinet", + "649": "megalith, megalithic structure", + "650": "microphone, mike", + "651": "microwave, microwave oven", + "652": "military uniform", + "653": "milk can", + "654": "minibus", + "655": "miniskirt, mini", + "656": "minivan", + "657": "missile", + "658": "mitten", + "659": "mixing bowl", + "660": "mobile home, manufactured home", + "661": "Model T", + "662": "modem", + "663": "monastery", + "664": "monitor", + "665": "moped", + "666": "mortar", + "667": "mortarboard", + "668": "mosque", + "669": "mosquito net", + "670": "motor scooter, scooter", + "671": "mountain bike, all-terrain bike, off-roader", + "672": "mountain tent", + "673": "mouse, computer mouse", + "674": "mousetrap", + "675": "moving van", + "676": "muzzle", + "677": "nail", + "678": "neck brace", + "679": "necklace", + "680": "nipple", + "681": "notebook, notebook computer", + "682": "obelisk", + "683": "oboe, hautboy, hautbois", + "684": "ocarina, sweet potato", + "685": "odometer, hodometer, mileometer, milometer", + "686": "oil filter", + "687": "organ, pipe organ", + "688": "oscilloscope, scope, cathode-ray oscilloscope, CRO", + "689": "overskirt", + "690": "oxcart", + "691": "oxygen mask", + "692": "packet", + "693": "paddle, boat paddle", + "694": "paddlewheel, paddle wheel", + "695": "padlock", + "696": "paintbrush", + "697": "pajama, pyjama, pj's, jammies", + "698": "palace", + "699": "panpipe, pandean pipe, syrinx", + "700": "paper towel", + "701": "parachute, chute", + "702": "parallel bars, bars", + "703": "park bench", + "704": "parking meter", + "705": "passenger car, coach, carriage", + "706": "patio, terrace", + "707": "pay-phone, pay-station", + "708": "pedestal, plinth, footstall", + "709": "pencil box, pencil case", + "710": "pencil sharpener", + "711": "perfume, essence", + "712": "Petri dish", + "713": "photocopier", + "714": "pick, plectrum, plectron", + "715": "pickelhaube", + "716": "picket fence, paling", + "717": "pickup, pickup truck", + "718": "pier", + "719": "piggy bank, penny bank", + "720": "pill bottle", + "721": "pillow", + "722": "ping-pong ball", + "723": "pinwheel", + "724": "pirate, pirate ship", + "725": "pitcher, ewer", + "726": "plane, carpenter's plane, woodworking plane", + "727": "planetarium", + "728": "plastic bag", + "729": "plate rack", + "730": "plow, plough", + "731": "plunger, plumber's helper", + "732": "Polaroid camera, Polaroid Land camera", + "733": "pole", + "734": "police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria", + "735": "poncho", + "736": "pool table, billiard table, snooker table", + "737": "pop bottle, soda bottle", + "738": "pot, flowerpot", + "739": "potter's wheel", + "740": "power drill", + "741": "prayer rug, prayer mat", + "742": "printer", + "743": "prison, prison house", + "744": "projectile, missile", + "745": "projector", + "746": "puck, hockey puck", + "747": "punching bag, punch bag, punching ball, punchball", + "748": "purse", + "749": "quill, quill pen", + "750": "quilt, comforter, comfort, puff", + "751": "racer, race car, racing car", + "752": "racket, racquet", + "753": "radiator", + "754": "radio, wireless", + "755": "radio telescope, radio reflector", + "756": "rain barrel", + "757": "recreational vehicle, RV, R.V.", + "758": "reel", + "759": "reflex camera", + "760": "refrigerator, icebox", + "761": "remote control, remote", + "762": "restaurant, eating house, eating place, eatery", + "763": "revolver, six-gun, six-shooter", + "764": "rifle", + "765": "rocking chair, rocker", + "766": "rotisserie", + "767": "rubber eraser, rubber, pencil eraser", + "768": "rugby ball", + "769": "rule, ruler", + "770": "running shoe", + "771": "safe", + "772": "safety pin", + "773": "saltshaker, salt shaker", + "774": "sandal", + "775": "sarong", + "776": "sax, saxophone", + "777": "scabbard", + "778": "scale, weighing machine", + "779": "school bus", + "780": "schooner", + "781": "scoreboard", + "782": "screen, CRT screen", + "783": "screw", + "784": "screwdriver", + "785": "seat belt, seatbelt", + "786": "sewing machine", + "787": "shield, buckler", + "788": "shoe shop, shoe-shop, shoe store", + "789": "shoji", + "790": "shopping basket", + "791": "shopping cart", + "792": "shovel", + "793": "shower cap", + "794": "shower curtain", + "795": "ski", + "796": "ski mask", + "797": "sleeping bag", + "798": "slide rule, slipstick", + "799": "sliding door", + "800": "slot, one-armed bandit", + "801": "snorkel", + "802": "snowmobile", + "803": "snowplow, snowplough", + "804": "soap dispenser", + "805": "soccer ball", + "806": "sock", + "807": "solar dish, solar collector, solar furnace", + "808": "sombrero", + "809": "soup bowl", + "810": "space bar", + "811": "space heater", + "812": "space shuttle", + "813": "spatula", + "814": "speedboat", + "815": "spider web, spider's web", + "816": "spindle", + "817": "sports car, sport car", + "818": "spotlight, spot", + "819": "stage", + "820": "steam locomotive", + "821": "steel arch bridge", + "822": "steel drum", + "823": "stethoscope", + "824": "stole", + "825": "stone wall", + "826": "stopwatch, stop watch", + "827": "stove", + "828": "strainer", + "829": "streetcar, tram, tramcar, trolley, trolley car", + "830": "stretcher", + "831": "studio couch, day bed", + "832": "stupa, tope", + "833": "submarine, pigboat, sub, U-boat", + "834": "suit, suit of clothes", + "835": "sundial", + "836": "sunglass", + "837": "sunglasses, dark glasses, shades", + "838": "sunscreen, sunblock, sun blocker", + "839": "suspension bridge", + "840": "swab, swob, mop", + "841": "sweatshirt", + "842": "swimming trunks, bathing trunks", + "843": "swing", + "844": "switch, electric switch, electrical switch", + "845": "syringe", + "846": "table lamp", + "847": "tank, army tank, armored combat vehicle, armoured combat vehicle", + "848": "tape player", + "849": "teapot", + "850": "teddy, teddy bear", + "851": "television, television system", + "852": "tennis ball", + "853": "thatch, thatched roof", + "854": "theater curtain, theatre curtain", + "855": "thimble", + "856": "thresher, thrasher, threshing machine", + "857": "throne", + "858": "tile roof", + "859": "toaster", + "860": "tobacco shop, tobacconist shop, tobacconist", + "861": "toilet seat", + "862": "torch", + "863": "totem pole", + "864": "tow truck, tow car, wrecker", + "865": "toyshop", + "866": "tractor", + "867": "trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi", + "868": "tray", + "869": "trench coat", + "870": "tricycle, trike, velocipede", + "871": "trimaran", + "872": "tripod", + "873": "triumphal arch", + "874": "trolleybus, trolley coach, trackless trolley", + "875": "trombone", + "876": "tub, vat", + "877": "turnstile", + "878": "typewriter keyboard", + "879": "umbrella", + "880": "unicycle, monocycle", + "881": "upright, upright piano", + "882": "vacuum, vacuum cleaner", + "883": "vase", + "884": "vault", + "885": "velvet", + "886": "vending machine", + "887": "vestment", + "888": "viaduct", + "889": "violin, fiddle", + "890": "volleyball", + "891": "waffle iron", + "892": "wall clock", + "893": "wallet, billfold, notecase, pocketbook", + "894": "wardrobe, closet, press", + "895": "warplane, military plane", + "896": "washbasin, handbasin, washbowl, lavabo, wash-hand basin", + "897": "washer, automatic washer, washing machine", + "898": "water bottle", + "899": "water jug", + "900": "water tower", + "901": "whiskey jug", + "902": "whistle", + "903": "wig", + "904": "window screen", + "905": "window shade", + "906": "Windsor tie", + "907": "wine bottle", + "908": "wing", + "909": "wok", + "910": "wooden spoon", + "911": "wool, woolen, woollen", + "912": "worm fence, snake fence, snake-rail fence, Virginia fence", + "913": "wreck", + "914": "yawl", + "915": "yurt", + "916": "web site, website, internet site, site", + "917": "comic book", + "918": "crossword puzzle, crossword", + "919": "street sign", + "920": "traffic light, traffic signal, stoplight", + "921": "book jacket, dust cover, dust jacket, dust wrapper", + "922": "menu", + "923": "plate", + "924": "guacamole", + "925": "consomme", + "926": "hot pot, hotpot", + "927": "trifle", + "928": "ice cream, icecream", + "929": "ice lolly, lolly, lollipop, popsicle", + "930": "French loaf", + "931": "bagel, beigel", + "932": "pretzel", + "933": "cheeseburger", + "934": "hotdog, hot dog, red hot", + "935": "mashed potato", + "936": "head cabbage", + "937": "broccoli", + "938": "cauliflower", + "939": "zucchini, courgette", + "940": "spaghetti squash", + "941": "acorn squash", + "942": "butternut squash", + "943": "cucumber, cuke", + "944": "artichoke, globe artichoke", + "945": "bell pepper", + "946": "cardoon", + "947": "mushroom", + "948": "Granny Smith", + "949": "strawberry", + "950": "orange", + "951": "lemon", + "952": "fig", + "953": "pineapple, ananas", + "954": "banana", + "955": "jackfruit, jak, jack", + "956": "custard apple", + "957": "pomegranate", + "958": "hay", + "959": "carbonara", + "960": "chocolate sauce, chocolate syrup", + "961": "dough", + "962": "meat loaf, meatloaf", + "963": "pizza, pizza pie", + "964": "potpie", + "965": "burrito", + "966": "red wine", + "967": "espresso", + "968": "cup", + "969": "eggnog", + "970": "alp", + "971": "bubble", + "972": "cliff, drop, drop-off", + "973": "coral reef", + "974": "geyser", + "975": "lakeside, lakeshore", + "976": "promontory, headland, head, foreland", + "977": "sandbar, sand bar", + "978": "seashore, coast, seacoast, sea-coast", + "979": "valley, vale", + "980": "volcano", + "981": "ballplayer, baseball player", + "982": "groom, bridegroom", + "983": "scuba diver", + "984": "rapeseed", + "985": "daisy", + "986": "yellow lady's slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum", + "987": "corn", + "988": "acorn", + "989": "hip, rose hip, rosehip", + "990": "buckeye, horse chestnut, conker", + "991": "coral fungus", + "992": "agaric", + "993": "gyromitra", + "994": "stinkhorn, carrion fungus", + "995": "earthstar", + "996": "hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa", + "997": "bolete", + "998": "ear, spike, capitulum", + "999": "toilet tissue, toilet paper, bathroom tissue" + }, + "image_size": 256, + "initializer_range": 0.02, + "label2id": { + "Afghan hound, Afghan": 160, + "African chameleon, Chamaeleo chamaeleon": 47, + "African crocodile, Nile crocodile, Crocodylus niloticus": 49, + "African elephant, Loxodonta africana": 386, + "African grey, African gray, Psittacus erithacus": 87, + "African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus": 275, + "Airedale, Airedale terrier": 191, + "American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier": 180, + "American alligator, Alligator mississipiensis": 50, + "American black bear, black bear, Ursus americanus, Euarctos americanus": 295, + "American chameleon, anole, Anolis carolinensis": 40, + "American coot, marsh hen, mud hen, water hen, Fulica americana": 137, + "American egret, great white heron, Egretta albus": 132, + "American lobster, Northern lobster, Maine lobster, Homarus americanus": 122, + "Angora, Angora rabbit": 332, + "Appenzeller": 240, + "Arabian camel, dromedary, Camelus dromedarius": 354, + "Arctic fox, white fox, Alopex lagopus": 279, + "Australian terrier": 193, + "Band Aid": 419, + "Bedlington terrier": 181, + "Bernese mountain dog": 239, + "Blenheim spaniel": 156, + "Border collie": 232, + "Border terrier": 182, + "Boston bull, Boston terrier": 195, + "Bouvier des Flandres, Bouviers des Flandres": 233, + "Brabancon griffon": 262, + "Brittany spaniel": 215, + "CD player": 485, + "Cardigan, Cardigan Welsh corgi": 264, + "Chesapeake Bay retriever": 209, + "Chihuahua": 151, + "Christmas stocking": 496, + "Crock Pot": 521, + "Dandie Dinmont, Dandie Dinmont terrier": 194, + "Doberman, Doberman pinscher": 236, + "Dungeness crab, Cancer magister": 118, + "Dutch oven": 544, + "Egyptian cat": 285, + "English foxhound": 167, + "English setter": 212, + "English springer, English springer spaniel": 217, + "EntleBucher": 241, + "Eskimo dog, husky": 248, + "European fire salamander, Salamandra salamandra": 25, + "European gallinule, Porphyrio porphyrio": 136, + "French bulldog": 245, + "French horn, horn": 566, + "French loaf": 930, + "German shepherd, German shepherd dog, German police dog, alsatian": 235, + "German short-haired pointer": 210, + "Gila monster, Heloderma suspectum": 45, + "Gordon setter": 214, + "Granny Smith": 948, + "Great Dane": 246, + "Great Pyrenees": 257, + "Greater Swiss Mountain dog": 238, + "Ibizan hound, Ibizan Podenco": 173, + "Indian cobra, Naja naja": 63, + "Indian elephant, Elephas maximus": 385, + "Irish setter, red setter": 213, + "Irish terrier": 184, + "Irish water spaniel": 221, + "Irish wolfhound": 170, + "Italian greyhound": 171, + "Japanese spaniel": 152, + "Kerry blue terrier": 183, + "Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis": 48, + "Labrador retriever": 208, + "Lakeland terrier": 189, + "Leonberg": 255, + "Lhasa, Lhasa apso": 204, + "Loafer": 630, + "Madagascar cat, ring-tailed lemur, Lemur catta": 383, + "Maltese dog, Maltese terrier, Maltese": 153, + "Mexican hairless": 268, + "Model T": 661, + "Newfoundland, Newfoundland dog": 256, + "Norfolk terrier": 185, + "Norwegian elkhound, elkhound": 174, + "Norwich terrier": 186, + "Old English sheepdog, bobtail": 229, + "Pekinese, Pekingese, Peke": 154, + "Pembroke, Pembroke Welsh corgi": 263, + "Persian cat": 283, + "Petri dish": 712, + "Polaroid camera, Polaroid Land camera": 732, + "Pomeranian": 259, + "Rhodesian ridgeback": 159, + "Rottweiler": 234, + "Saint Bernard, St Bernard": 247, + "Saluki, gazelle hound": 176, + "Samoyed, Samoyede": 258, + "Scotch terrier, Scottish terrier, Scottie": 199, + "Scottish deerhound, deerhound": 177, + "Sealyham terrier, Sealyham": 190, + "Shetland sheepdog, Shetland sheep dog, Shetland": 230, + "Shih-Tzu": 155, + "Siamese cat, Siamese": 284, + "Siberian husky": 250, + "Staffordshire bullterrier, Staffordshire bull terrier": 179, + "Sussex spaniel": 220, + "Tibetan mastiff": 244, + "Tibetan terrier, chrysanthemum dog": 200, + "Walker hound, Walker foxhound": 166, + "Weimaraner": 178, + "Welsh springer spaniel": 218, + "West Highland white terrier": 203, + "Windsor tie": 906, + "Yorkshire terrier": 187, + "abacus": 398, + "abaya": 399, + "academic gown, academic robe, judge's robe": 400, + "accordion, piano accordion, squeeze box": 401, + "acorn": 988, + "acorn squash": 941, + "acoustic guitar": 402, + "admiral": 321, + "affenpinscher, monkey pinscher, monkey dog": 252, + "agama": 42, + "agaric": 992, + "aircraft carrier, carrier, flattop, attack aircraft carrier": 403, + "airliner": 404, + "airship, dirigible": 405, + "albatross, mollymawk": 146, + "alligator lizard": 44, + "alp": 970, + "altar": 406, + "ambulance": 407, + "amphibian, amphibious vehicle": 408, + "analog clock": 409, + "anemone fish": 393, + "ant, emmet, pismire": 310, + "apiary, bee house": 410, + "apron": 411, + "armadillo": 363, + "artichoke, globe artichoke": 944, + "ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin": 412, + "assault rifle, assault gun": 413, + "axolotl, mud puppy, Ambystoma mexicanum": 29, + "baboon": 372, + "backpack, back pack, knapsack, packsack, rucksack, haversack": 414, + "badger": 362, + "bagel, beigel": 931, + "bakery, bakeshop, bakehouse": 415, + "balance beam, beam": 416, + "bald eagle, American eagle, Haliaeetus leucocephalus": 22, + "balloon": 417, + "ballplayer, baseball player": 981, + "ballpoint, ballpoint pen, ballpen, Biro": 418, + "banana": 954, + "banded gecko": 38, + "banjo": 420, + "bannister, banister, balustrade, balusters, handrail": 421, + "barbell": 422, + "barber chair": 423, + "barbershop": 424, + "barn": 425, + "barn spider, Araneus cavaticus": 73, + "barometer": 426, + "barracouta, snoek": 389, + "barrel, cask": 427, + "barrow, garden cart, lawn cart, wheelbarrow": 428, + "baseball": 429, + "basenji": 253, + "basketball": 430, + "basset, basset hound": 161, + "bassinet": 431, + "bassoon": 432, + "bath towel": 434, + "bathing cap, swimming cap": 433, + "bathtub, bathing tub, bath, tub": 435, + "beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon": 436, + "beacon, lighthouse, beacon light, pharos": 437, + "beagle": 162, + "beaker": 438, + "bearskin, busby, shako": 439, + "beaver": 337, + "bee": 309, + "bee eater": 92, + "beer bottle": 440, + "beer glass": 441, + "bell cote, bell cot": 442, + "bell pepper": 945, + "bib": 443, + "bicycle-built-for-two, tandem bicycle, tandem": 444, + "bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis": 349, + "bikini, two-piece": 445, + "binder, ring-binder": 446, + "binoculars, field glasses, opera glasses": 447, + "birdhouse": 448, + "bison": 347, + "bittern": 133, + "black and gold garden spider, Argiope aurantia": 72, + "black grouse": 80, + "black stork, Ciconia nigra": 128, + "black swan, Cygnus atratus": 100, + "black widow, Latrodectus mactans": 75, + "black-and-tan coonhound": 165, + "black-footed ferret, ferret, Mustela nigripes": 359, + "bloodhound, sleuthhound": 163, + "bluetick": 164, + "boa constrictor, Constrictor constrictor": 61, + "boathouse": 449, + "bobsled, bobsleigh, bob": 450, + "bolete": 997, + "bolo tie, bolo, bola tie, bola": 451, + "bonnet, poke bonnet": 452, + "book jacket, dust cover, dust jacket, dust wrapper": 921, + "bookcase": 453, + "bookshop, bookstore, bookstall": 454, + "borzoi, Russian wolfhound": 169, + "bottlecap": 455, + "bow": 456, + "bow tie, bow-tie, bowtie": 457, + "box turtle, box tortoise": 37, + "boxer": 242, + "brain coral": 109, + "brambling, Fringilla montifringilla": 10, + "brass, memorial tablet, plaque": 458, + "brassiere, bra, bandeau": 459, + "breakwater, groin, groyne, mole, bulwark, seawall, jetty": 460, + "breastplate, aegis, egis": 461, + "briard": 226, + "broccoli": 937, + "broom": 462, + "brown bear, bruin, Ursus arctos": 294, + "bubble": 971, + "bucket, pail": 463, + "buckeye, horse chestnut, conker": 990, + "buckle": 464, + "bulbul": 16, + "bull mastiff": 243, + "bullet train, bullet": 466, + "bulletproof vest": 465, + "bullfrog, Rana catesbeiana": 30, + "burrito": 965, + "bustard": 138, + "butcher shop, meat market": 467, + "butternut squash": 942, + "cab, hack, taxi, taxicab": 468, + "cabbage butterfly": 324, + "cairn, cairn terrier": 192, + "caldron, cauldron": 469, + "can opener, tin opener": 473, + "candle, taper, wax light": 470, + "cannon": 471, + "canoe": 472, + "capuchin, ringtail, Cebus capucinus": 378, + "car mirror": 475, + "car wheel": 479, + "carbonara": 959, + "cardigan": 474, + "cardoon": 946, + "carousel, carrousel, merry-go-round, roundabout, whirligig": 476, + "carpenter's kit, tool kit": 477, + "carton": 478, + "cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM": 480, + "cassette": 481, + "cassette player": 482, + "castle": 483, + "catamaran": 484, + "cauliflower": 938, + "cello, violoncello": 486, + "cellular telephone, cellular phone, cellphone, cell, mobile phone": 487, + "centipede": 79, + "chain": 488, + "chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour": 490, + "chain saw, chainsaw": 491, + "chainlink fence": 489, + "chambered nautilus, pearly nautilus, nautilus": 117, + "cheeseburger": 933, + "cheetah, chetah, Acinonyx jubatus": 293, + "chest": 492, + "chickadee": 19, + "chiffonier, commode": 493, + "chime, bell, gong": 494, + "chimpanzee, chimp, Pan troglodytes": 367, + "china cabinet, china closet": 495, + "chiton, coat-of-mail shell, sea cradle, polyplacophore": 116, + "chocolate sauce, chocolate syrup": 960, + "chow, chow chow": 260, + "church, church building": 497, + "cicada, cicala": 316, + "cinema, movie theater, movie theatre, movie house, picture palace": 498, + "cleaver, meat cleaver, chopper": 499, + "cliff dwelling": 500, + "cliff, drop, drop-off": 972, + "cloak": 501, + "clog, geta, patten, sabot": 502, + "clumber, clumber spaniel": 216, + "cock": 7, + "cocker spaniel, English cocker spaniel, cocker": 219, + "cockroach, roach": 314, + "cocktail shaker": 503, + "coffee mug": 504, + "coffeepot": 505, + "coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch": 391, + "coil, spiral, volute, whorl, helix": 506, + "collie": 231, + "colobus, colobus monkey": 375, + "combination lock": 507, + "comic book": 917, + "common iguana, iguana, Iguana iguana": 39, + "common newt, Triturus vulgaris": 26, + "computer keyboard, keypad": 508, + "conch": 112, + "confectionery, confectionary, candy store": 509, + "consomme": 925, + "container ship, containership, container vessel": 510, + "convertible": 511, + "coral fungus": 991, + "coral reef": 973, + "corkscrew, bottle screw": 512, + "corn": 987, + "cornet, horn, trumpet, trump": 513, + "coucal": 91, + "cougar, puma, catamount, mountain lion, painter, panther, Felis concolor": 286, + "cowboy boot": 514, + "cowboy hat, ten-gallon hat": 515, + "coyote, prairie wolf, brush wolf, Canis latrans": 272, + "cradle": 516, + "crane": 517, + "crash helmet": 518, + "crate": 519, + "crayfish, crawfish, crawdad, crawdaddy": 124, + "crib, cot": 520, + "cricket": 312, + "croquet ball": 522, + "crossword puzzle, crossword": 918, + "crutch": 523, + "cucumber, cuke": 943, + "cuirass": 524, + "cup": 968, + "curly-coated retriever": 206, + "custard apple": 956, + "daisy": 985, + "dalmatian, coach dog, carriage dog": 251, + "dam, dike, dyke": 525, + "damselfly": 320, + "desk": 526, + "desktop computer": 527, + "dhole, Cuon alpinus": 274, + "dial telephone, dial phone": 528, + "diamondback, diamondback rattlesnake, Crotalus adamanteus": 67, + "diaper, nappy, napkin": 529, + "digital clock": 530, + "digital watch": 531, + "dingo, warrigal, warragal, Canis dingo": 273, + "dining table, board": 532, + "dishrag, dishcloth": 533, + "dishwasher, dish washer, dishwashing machine": 534, + "disk brake, disc brake": 535, + "dock, dockage, docking facility": 536, + "dogsled, dog sled, dog sleigh": 537, + "dome": 538, + "doormat, welcome mat": 539, + "dough": 961, + "dowitcher": 142, + "dragonfly, darning needle, devil's darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk": 319, + "drake": 97, + "drilling platform, offshore rig": 540, + "drum, membranophone, tympan": 541, + "drumstick": 542, + "dugong, Dugong dugon": 149, + "dumbbell": 543, + "dung beetle": 305, + "ear, spike, capitulum": 998, + "earthstar": 995, + "echidna, spiny anteater, anteater": 102, + "eel": 390, + "eft": 27, + "eggnog": 969, + "electric fan, blower": 545, + "electric guitar": 546, + "electric locomotive": 547, + "electric ray, crampfish, numbfish, torpedo": 5, + "entertainment center": 548, + "envelope": 549, + "espresso": 967, + "espresso maker": 550, + "face powder": 551, + "feather boa, boa": 552, + "fiddler crab": 120, + "fig": 952, + "file, file cabinet, filing cabinet": 553, + "fire engine, fire truck": 555, + "fire screen, fireguard": 556, + "fireboat": 554, + "flagpole, flagstaff": 557, + "flamingo": 130, + "flat-coated retriever": 205, + "flatworm, platyhelminth": 110, + "flute, transverse flute": 558, + "fly": 308, + "folding chair": 559, + "football helmet": 560, + "forklift": 561, + "fountain": 562, + "fountain pen": 563, + "four-poster": 564, + "fox squirrel, eastern fox squirrel, Sciurus niger": 335, + "freight car": 565, + "frilled lizard, Chlamydosaurus kingi": 43, + "frying pan, frypan, skillet": 567, + "fur coat": 568, + "gar, garfish, garpike, billfish, Lepisosteus osseus": 395, + "garbage truck, dustcart": 569, + "garden spider, Aranea diademata": 74, + "garter snake, grass snake": 57, + "gas pump, gasoline pump, petrol pump, island dispenser": 571, + "gasmask, respirator, gas helmet": 570, + "gazelle": 353, + "geyser": 974, + "giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca": 388, + "giant schnauzer": 197, + "gibbon, Hylobates lar": 368, + "go-kart": 573, + "goblet": 572, + "golden retriever": 207, + "goldfinch, Carduelis carduelis": 11, + "goldfish, Carassius auratus": 1, + "golf ball": 574, + "golfcart, golf cart": 575, + "gondola": 576, + "gong, tam-tam": 577, + "goose": 99, + "gorilla, Gorilla gorilla": 366, + "gown": 578, + "grand piano, grand": 579, + "grasshopper, hopper": 311, + "great grey owl, great gray owl, Strix nebulosa": 24, + "great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias": 2, + "green lizard, Lacerta viridis": 46, + "green mamba": 64, + "green snake, grass snake": 55, + "greenhouse, nursery, glasshouse": 580, + "grey fox, gray fox, Urocyon cinereoargenteus": 280, + "grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus": 147, + "grille, radiator grille": 581, + "grocery store, grocery, food market, market": 582, + "groenendael": 224, + "groom, bridegroom": 982, + "ground beetle, carabid beetle": 302, + "guacamole": 924, + "guenon, guenon monkey": 370, + "guillotine": 583, + "guinea pig, Cavia cobaya": 338, + "gyromitra": 993, + "hair slide": 584, + "hair spray": 585, + "half track": 586, + "hammer": 587, + "hammerhead, hammerhead shark": 4, + "hamper": 588, + "hamster": 333, + "hand blower, blow dryer, blow drier, hair dryer, hair drier": 589, + "hand-held computer, hand-held microcomputer": 590, + "handkerchief, hankie, hanky, hankey": 591, + "hard disc, hard disk, fixed disk": 592, + "hare": 331, + "harmonica, mouth organ, harp, mouth harp": 593, + "harp": 594, + "hartebeest": 351, + "harvester, reaper": 595, + "harvestman, daddy longlegs, Phalangium opilio": 70, + "hatchet": 596, + "hay": 958, + "head cabbage": 936, + "hen": 8, + "hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa": 996, + "hermit crab": 125, + "hip, rose hip, rosehip": 989, + "hippopotamus, hippo, river horse, Hippopotamus amphibius": 344, + "hog, pig, grunter, squealer, Sus scrofa": 341, + "hognose snake, puff adder, sand viper": 54, + "holster": 597, + "home theater, home theatre": 598, + "honeycomb": 599, + "hook, claw": 600, + "hoopskirt, crinoline": 601, + "horizontal bar, high bar": 602, + "hornbill": 93, + "horned viper, cerastes, sand viper, horned asp, Cerastes cornutus": 66, + "horse cart, horse-cart": 603, + "hot pot, hotpot": 926, + "hotdog, hot dog, red hot": 934, + "hourglass": 604, + "house finch, linnet, Carpodacus mexicanus": 12, + "howler monkey, howler": 379, + "hummingbird": 94, + "hyena, hyaena": 276, + "iPod": 605, + "ibex, Capra ibex": 350, + "ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus": 296, + "ice cream, icecream": 928, + "ice lolly, lolly, lollipop, popsicle": 929, + "impala, Aepyceros melampus": 352, + "indigo bunting, indigo finch, indigo bird, Passerina cyanea": 14, + "indri, indris, Indri indri, Indri brevicaudatus": 384, + "iron, smoothing iron": 606, + "isopod": 126, + "jacamar": 95, + "jack-o'-lantern": 607, + "jackfruit, jak, jack": 955, + "jaguar, panther, Panthera onca, Felis onca": 290, + "jay": 17, + "jean, blue jean, denim": 608, + "jeep, landrover": 609, + "jellyfish": 107, + "jersey, T-shirt, tee shirt": 610, + "jigsaw puzzle": 611, + "jinrikisha, ricksha, rickshaw": 612, + "joystick": 613, + "junco, snowbird": 13, + "keeshond": 261, + "kelpie": 227, + "killer whale, killer, orca, grampus, sea wolf, Orcinus orca": 148, + "kimono": 614, + "king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica": 121, + "king penguin, Aptenodytes patagonica": 145, + "king snake, kingsnake": 56, + "kit fox, Vulpes macrotis": 278, + "kite": 21, + "knee pad": 615, + "knot": 616, + "koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus": 105, + "komondor": 228, + "kuvasz": 222, + "lab coat, laboratory coat": 617, + "lacewing, lacewing fly": 318, + "ladle": 618, + "ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle": 301, + "lakeside, lakeshore": 975, + "lampshade, lamp shade": 619, + "langur": 374, + "laptop, laptop computer": 620, + "lawn mower, mower": 621, + "leaf beetle, chrysomelid": 304, + "leafhopper": 317, + "leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea": 34, + "lemon": 951, + "lens cap, lens cover": 622, + "leopard, Panthera pardus": 288, + "lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens": 387, + "letter opener, paper knife, paperknife": 623, + "library": 624, + "lifeboat": 625, + "lighter, light, igniter, ignitor": 626, + "limousine, limo": 627, + "limpkin, Aramus pictus": 135, + "liner, ocean liner": 628, + "lion, king of beasts, Panthera leo": 291, + "lionfish": 396, + "lipstick, lip rouge": 629, + "little blue heron, Egretta caerulea": 131, + "llama": 355, + "loggerhead, loggerhead turtle, Caretta caretta": 33, + "long-horned beetle, longicorn, longicorn beetle": 303, + "lorikeet": 90, + "lotion": 631, + "loudspeaker, speaker, speaker unit, loudspeaker system, speaker system": 632, + "loupe, jeweler's loupe": 633, + "lumbermill, sawmill": 634, + "lycaenid, lycaenid butterfly": 326, + "lynx, catamount": 287, + "macaque": 373, + "macaw": 88, + "magnetic compass": 635, + "magpie": 18, + "mailbag, postbag": 636, + "mailbox, letter box": 637, + "maillot": 638, + "maillot, tank suit": 639, + "malamute, malemute, Alaskan malamute": 249, + "malinois": 225, + "manhole cover": 640, + "mantis, mantid": 315, + "maraca": 641, + "marimba, xylophone": 642, + "marmoset": 377, + "marmot": 336, + "mashed potato": 935, + "mask": 643, + "matchstick": 644, + "maypole": 645, + "maze, labyrinth": 646, + "measuring cup": 647, + "meat loaf, meatloaf": 962, + "medicine chest, medicine cabinet": 648, + "meerkat, mierkat": 299, + "megalith, megalithic structure": 649, + "menu": 922, + "microphone, mike": 650, + "microwave, microwave oven": 651, + "military uniform": 652, + "milk can": 653, + "miniature pinscher": 237, + "miniature poodle": 266, + "miniature schnauzer": 196, + "minibus": 654, + "miniskirt, mini": 655, + "minivan": 656, + "mink": 357, + "missile": 657, + "mitten": 658, + "mixing bowl": 659, + "mobile home, manufactured home": 660, + "modem": 662, + "monarch, monarch butterfly, milkweed butterfly, Danaus plexippus": 323, + "monastery": 663, + "mongoose": 298, + "monitor": 664, + "moped": 665, + "mortar": 666, + "mortarboard": 667, + "mosque": 668, + "mosquito net": 669, + "motor scooter, scooter": 670, + "mountain bike, all-terrain bike, off-roader": 671, + "mountain tent": 672, + "mouse, computer mouse": 673, + "mousetrap": 674, + "moving van": 675, + "mud turtle": 35, + "mushroom": 947, + "muzzle": 676, + "nail": 677, + "neck brace": 678, + "necklace": 679, + "nematode, nematode worm, roundworm": 111, + "night snake, Hypsiglena torquata": 60, + "nipple": 680, + "notebook, notebook computer": 681, + "obelisk": 682, + "oboe, hautboy, hautbois": 683, + "ocarina, sweet potato": 684, + "odometer, hodometer, mileometer, milometer": 685, + "oil filter": 686, + "orange": 950, + "orangutan, orang, orangutang, Pongo pygmaeus": 365, + "organ, pipe organ": 687, + "oscilloscope, scope, cathode-ray oscilloscope, CRO": 688, + "ostrich, Struthio camelus": 9, + "otter": 360, + "otterhound, otter hound": 175, + "overskirt": 689, + "ox": 345, + "oxcart": 690, + "oxygen mask": 691, + "oystercatcher, oyster catcher": 143, + "packet": 692, + "paddle, boat paddle": 693, + "paddlewheel, paddle wheel": 694, + "padlock": 695, + "paintbrush": 696, + "pajama, pyjama, pj's, jammies": 697, + "palace": 698, + "panpipe, pandean pipe, syrinx": 699, + "paper towel": 700, + "papillon": 157, + "parachute, chute": 701, + "parallel bars, bars": 702, + "park bench": 703, + "parking meter": 704, + "partridge": 86, + "passenger car, coach, carriage": 705, + "patas, hussar monkey, Erythrocebus patas": 371, + "patio, terrace": 706, + "pay-phone, pay-station": 707, + "peacock": 84, + "pedestal, plinth, footstall": 708, + "pelican": 144, + "pencil box, pencil case": 709, + "pencil sharpener": 710, + "perfume, essence": 711, + "photocopier": 713, + "pick, plectrum, plectron": 714, + "pickelhaube": 715, + "picket fence, paling": 716, + "pickup, pickup truck": 717, + "pier": 718, + "piggy bank, penny bank": 719, + "pill bottle": 720, + "pillow": 721, + "pineapple, ananas": 953, + "ping-pong ball": 722, + "pinwheel": 723, + "pirate, pirate ship": 724, + "pitcher, ewer": 725, + "pizza, pizza pie": 963, + "plane, carpenter's plane, woodworking plane": 726, + "planetarium": 727, + "plastic bag": 728, + "plate": 923, + "plate rack": 729, + "platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus": 103, + "plow, plough": 730, + "plunger, plumber's helper": 731, + "pole": 733, + "polecat, fitch, foulmart, foumart, Mustela putorius": 358, + "police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria": 734, + "pomegranate": 957, + "poncho": 735, + "pool table, billiard table, snooker table": 736, + "pop bottle, soda bottle": 737, + "porcupine, hedgehog": 334, + "pot, flowerpot": 738, + "potpie": 964, + "potter's wheel": 739, + "power drill": 740, + "prairie chicken, prairie grouse, prairie fowl": 83, + "prayer rug, prayer mat": 741, + "pretzel": 932, + "printer": 742, + "prison, prison house": 743, + "proboscis monkey, Nasalis larvatus": 376, + "projectile, missile": 744, + "projector": 745, + "promontory, headland, head, foreland": 976, + "ptarmigan": 81, + "puck, hockey puck": 746, + "puffer, pufferfish, blowfish, globefish": 397, + "pug, pug-dog": 254, + "punching bag, punch bag, punching ball, punchball": 747, + "purse": 748, + "quail": 85, + "quill, quill pen": 749, + "quilt, comforter, comfort, puff": 750, + "racer, race car, racing car": 751, + "racket, racquet": 752, + "radiator": 753, + "radio telescope, radio reflector": 755, + "radio, wireless": 754, + "rain barrel": 756, + "ram, tup": 348, + "rapeseed": 984, + "recreational vehicle, RV, R.V.": 757, + "red fox, Vulpes vulpes": 277, + "red wine": 966, + "red wolf, maned wolf, Canis rufus, Canis niger": 271, + "red-backed sandpiper, dunlin, Erolia alpina": 140, + "red-breasted merganser, Mergus serrator": 98, + "redbone": 168, + "redshank, Tringa totanus": 141, + "reel": 758, + "reflex camera": 759, + "refrigerator, icebox": 760, + "remote control, remote": 761, + "restaurant, eating house, eating place, eatery": 762, + "revolver, six-gun, six-shooter": 763, + "rhinoceros beetle": 306, + "rifle": 764, + "ringlet, ringlet butterfly": 322, + "ringneck snake, ring-necked snake, ring snake": 53, + "robin, American robin, Turdus migratorius": 15, + "rock beauty, Holocanthus tricolor": 392, + "rock crab, Cancer irroratus": 119, + "rock python, rock snake, Python sebae": 62, + "rocking chair, rocker": 765, + "rotisserie": 766, + "rubber eraser, rubber, pencil eraser": 767, + "ruddy turnstone, Arenaria interpres": 139, + "ruffed grouse, partridge, Bonasa umbellus": 82, + "rugby ball": 768, + "rule, ruler": 769, + "running shoe": 770, + "safe": 771, + "safety pin": 772, + "saltshaker, salt shaker": 773, + "sandal": 774, + "sandbar, sand bar": 977, + "sarong": 775, + "sax, saxophone": 776, + "scabbard": 777, + "scale, weighing machine": 778, + "schipperke": 223, + "school bus": 779, + "schooner": 780, + "scoreboard": 781, + "scorpion": 71, + "screen, CRT screen": 782, + "screw": 783, + "screwdriver": 784, + "scuba diver": 983, + "sea anemone, anemone": 108, + "sea cucumber, holothurian": 329, + "sea lion": 150, + "sea slug, nudibranch": 115, + "sea snake": 65, + "sea urchin": 328, + "seashore, coast, seacoast, sea-coast": 978, + "seat belt, seatbelt": 785, + "sewing machine": 786, + "shield, buckler": 787, + "shoe shop, shoe-shop, shoe store": 788, + "shoji": 789, + "shopping basket": 790, + "shopping cart": 791, + "shovel": 792, + "shower cap": 793, + "shower curtain": 794, + "siamang, Hylobates syndactylus, Symphalangus syndactylus": 369, + "sidewinder, horned rattlesnake, Crotalus cerastes": 68, + "silky terrier, Sydney silky": 201, + "ski": 795, + "ski mask": 796, + "skunk, polecat, wood pussy": 361, + "sleeping bag": 797, + "slide rule, slipstick": 798, + "sliding door": 799, + "slot, one-armed bandit": 800, + "sloth bear, Melursus ursinus, Ursus ursinus": 297, + "slug": 114, + "snail": 113, + "snorkel": 801, + "snow leopard, ounce, Panthera uncia": 289, + "snowmobile": 802, + "snowplow, snowplough": 803, + "soap dispenser": 804, + "soccer ball": 805, + "sock": 806, + "soft-coated wheaten terrier": 202, + "solar dish, solar collector, solar furnace": 807, + "sombrero": 808, + "sorrel": 339, + "soup bowl": 809, + "space bar": 810, + "space heater": 811, + "space shuttle": 812, + "spaghetti squash": 940, + "spatula": 813, + "speedboat": 814, + "spider monkey, Ateles geoffroyi": 381, + "spider web, spider's web": 815, + "spindle": 816, + "spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish": 123, + "spoonbill": 129, + "sports car, sport car": 817, + "spotlight, spot": 818, + "spotted salamander, Ambystoma maculatum": 28, + "squirrel monkey, Saimiri sciureus": 382, + "stage": 819, + "standard poodle": 267, + "standard schnauzer": 198, + "starfish, sea star": 327, + "steam locomotive": 820, + "steel arch bridge": 821, + "steel drum": 822, + "stethoscope": 823, + "stingray": 6, + "stinkhorn, carrion fungus": 994, + "stole": 824, + "stone wall": 825, + "stopwatch, stop watch": 826, + "stove": 827, + "strainer": 828, + "strawberry": 949, + "street sign": 919, + "streetcar, tram, tramcar, trolley, trolley car": 829, + "stretcher": 830, + "studio couch, day bed": 831, + "stupa, tope": 832, + "sturgeon": 394, + "submarine, pigboat, sub, U-boat": 833, + "suit, suit of clothes": 834, + "sulphur butterfly, sulfur butterfly": 325, + "sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita": 89, + "sundial": 835, + "sunglass": 836, + "sunglasses, dark glasses, shades": 837, + "sunscreen, sunblock, sun blocker": 838, + "suspension bridge": 839, + "swab, swob, mop": 840, + "sweatshirt": 841, + "swimming trunks, bathing trunks": 842, + "swing": 843, + "switch, electric switch, electrical switch": 844, + "syringe": 845, + "tabby, tabby cat": 281, + "table lamp": 846, + "tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui": 32, + "tank, army tank, armored combat vehicle, armoured combat vehicle": 847, + "tape player": 848, + "tarantula": 76, + "teapot": 849, + "teddy, teddy bear": 850, + "television, television system": 851, + "tench, Tinca tinca": 0, + "tennis ball": 852, + "terrapin": 36, + "thatch, thatched roof": 853, + "theater curtain, theatre curtain": 854, + "thimble": 855, + "three-toed sloth, ai, Bradypus tridactylus": 364, + "thresher, thrasher, threshing machine": 856, + "throne": 857, + "thunder snake, worm snake, Carphophis amoenus": 52, + "tick": 78, + "tiger beetle": 300, + "tiger cat": 282, + "tiger shark, Galeocerdo cuvieri": 3, + "tiger, Panthera tigris": 292, + "tile roof": 858, + "timber wolf, grey wolf, gray wolf, Canis lupus": 269, + "titi, titi monkey": 380, + "toaster": 859, + "tobacco shop, tobacconist shop, tobacconist": 860, + "toilet seat": 861, + "toilet tissue, toilet paper, bathroom tissue": 999, + "torch": 862, + "totem pole": 863, + "toucan": 96, + "tow truck, tow car, wrecker": 864, + "toy poodle": 265, + "toy terrier": 158, + "toyshop": 865, + "tractor": 866, + "traffic light, traffic signal, stoplight": 920, + "trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi": 867, + "tray": 868, + "tree frog, tree-frog": 31, + "trench coat": 869, + "triceratops": 51, + "tricycle, trike, velocipede": 870, + "trifle": 927, + "trilobite": 69, + "trimaran": 871, + "tripod": 872, + "triumphal arch": 873, + "trolleybus, trolley coach, trackless trolley": 874, + "trombone": 875, + "tub, vat": 876, + "turnstile": 877, + "tusker": 101, + "typewriter keyboard": 878, + "umbrella": 879, + "unicycle, monocycle": 880, + "upright, upright piano": 881, + "vacuum, vacuum cleaner": 882, + "valley, vale": 979, + "vase": 883, + "vault": 884, + "velvet": 885, + "vending machine": 886, + "vestment": 887, + "viaduct": 888, + "vine snake": 59, + "violin, fiddle": 889, + "vizsla, Hungarian pointer": 211, + "volcano": 980, + "volleyball": 890, + "vulture": 23, + "waffle iron": 891, + "walking stick, walkingstick, stick insect": 313, + "wall clock": 892, + "wallaby, brush kangaroo": 104, + "wallet, billfold, notecase, pocketbook": 893, + "wardrobe, closet, press": 894, + "warplane, military plane": 895, + "warthog": 343, + "washbasin, handbasin, washbowl, lavabo, wash-hand basin": 896, + "washer, automatic washer, washing machine": 897, + "water bottle": 898, + "water buffalo, water ox, Asiatic buffalo, Bubalus bubalis": 346, + "water jug": 899, + "water ouzel, dipper": 20, + "water snake": 58, + "water tower": 900, + "weasel": 356, + "web site, website, internet site, site": 916, + "weevil": 307, + "whippet": 172, + "whiptail, whiptail lizard": 41, + "whiskey jug": 901, + "whistle": 902, + "white stork, Ciconia ciconia": 127, + "white wolf, Arctic wolf, Canis lupus tundrarum": 270, + "wig": 903, + "wild boar, boar, Sus scrofa": 342, + "window screen": 904, + "window shade": 905, + "wine bottle": 907, + "wing": 908, + "wire-haired fox terrier": 188, + "wok": 909, + "wolf spider, hunting spider": 77, + "wombat": 106, + "wood rabbit, cottontail, cottontail rabbit": 330, + "wooden spoon": 910, + "wool, woolen, woollen": 911, + "worm fence, snake fence, snake-rail fence, Virginia fence": 912, + "wreck": 913, + "yawl": 914, + "yellow lady's slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum": 986, + "yurt": 915, + "zebra": 340, + "zucchini, courgette": 939 + }, + "layer_norm_eps": 1e-05, + "mlp_ratio": 2.0, + "model_type": "mobilevit", + "neck_hidden_sizes": [ + 4, + 8, + 16, + 24, + 32, + 40, + 160 + ], + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mobilevit", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 2, + "num_channels": 3, + "output_stride": 32, + "patch_size": 2, + "qkv_bias": true, + "semantic_loss_ignore_index": 255 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b499e2169427d86cfd5ea5795ff78579888b6c637e9f7ad212c17b21cd86a3cd/9fc767606b79a1a3f0b5.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b499e2169427d86cfd5ea5795ff78579888b6c637e9f7ad212c17b21cd86a3cd/9fc767606b79a1a3f0b5.json new file mode 100644 index 0000000000000000000000000000000000000000..f792de6473648017f8f9a8124a25d2dd21e3cb71 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b499e2169427d86cfd5ea5795ff78579888b6c637e9f7ad212c17b21cd86a3cd/9fc767606b79a1a3f0b5.json @@ -0,0 +1,2068 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-mobilevit", + "_task": "semantic-segmentation", + "architectures": [ + "MobileViTForImageClassification" + ], + "aspp_dropout_prob": 0.1, + "aspp_out_channels": 256, + "atrous_rates": [ + 6, + 12, + 18 + ], + "attention_probs_dropout_prob": 0.0, + "classifier_dropout_prob": 0.1, + "conv_kernel_size": 3, + "dtype": "float32", + "expand_ratio": 4.0, + "hidden_act": "silu", + "hidden_dropout_prob": 0.1, + "hidden_sizes": [ + 6, + 12, + 24 + ], + "id2label": { + "0": "tench, Tinca tinca", + "1": "goldfish, Carassius auratus", + "2": "great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias", + "3": "tiger shark, Galeocerdo cuvieri", + "4": "hammerhead, hammerhead shark", + "5": "electric ray, crampfish, numbfish, torpedo", + "6": "stingray", + "7": "cock", + "8": "hen", + "9": "ostrich, Struthio camelus", + "10": "brambling, Fringilla montifringilla", + "11": "goldfinch, Carduelis carduelis", + "12": "house finch, linnet, Carpodacus mexicanus", + "13": "junco, snowbird", + "14": "indigo bunting, indigo finch, indigo bird, Passerina cyanea", + "15": "robin, American robin, Turdus migratorius", + "16": "bulbul", + "17": "jay", + "18": "magpie", + "19": "chickadee", + "20": "water ouzel, dipper", + "21": "kite", + "22": "bald eagle, American eagle, Haliaeetus leucocephalus", + "23": "vulture", + "24": "great grey owl, great gray owl, Strix nebulosa", + "25": "European fire salamander, Salamandra salamandra", + "26": "common newt, Triturus vulgaris", + "27": "eft", + "28": "spotted salamander, Ambystoma maculatum", + "29": "axolotl, mud puppy, Ambystoma mexicanum", + "30": "bullfrog, Rana catesbeiana", + "31": "tree frog, tree-frog", + "32": "tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui", + "33": "loggerhead, loggerhead turtle, Caretta caretta", + "34": "leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea", + "35": "mud turtle", + "36": "terrapin", + "37": "box turtle, box tortoise", + "38": "banded gecko", + "39": "common iguana, iguana, Iguana iguana", + "40": "American chameleon, anole, Anolis carolinensis", + "41": "whiptail, whiptail lizard", + "42": "agama", + "43": "frilled lizard, Chlamydosaurus kingi", + "44": "alligator lizard", + "45": "Gila monster, Heloderma suspectum", + "46": "green lizard, Lacerta viridis", + "47": "African chameleon, Chamaeleo chamaeleon", + "48": "Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis", + "49": "African crocodile, Nile crocodile, Crocodylus niloticus", + "50": "American alligator, Alligator mississipiensis", + "51": "triceratops", + "52": "thunder snake, worm snake, Carphophis amoenus", + "53": "ringneck snake, ring-necked snake, ring snake", + "54": "hognose snake, puff adder, sand viper", + "55": "green snake, grass snake", + "56": "king snake, kingsnake", + "57": "garter snake, grass snake", + "58": "water snake", + "59": "vine snake", + "60": "night snake, Hypsiglena torquata", + "61": "boa constrictor, Constrictor constrictor", + "62": "rock python, rock snake, Python sebae", + "63": "Indian cobra, Naja naja", + "64": "green mamba", + "65": "sea snake", + "66": "horned viper, cerastes, sand viper, horned asp, Cerastes cornutus", + "67": "diamondback, diamondback rattlesnake, Crotalus adamanteus", + "68": "sidewinder, horned rattlesnake, Crotalus cerastes", + "69": "trilobite", + "70": "harvestman, daddy longlegs, Phalangium opilio", + "71": "scorpion", + "72": "black and gold garden spider, Argiope aurantia", + "73": "barn spider, Araneus cavaticus", + "74": "garden spider, Aranea diademata", + "75": "black widow, Latrodectus mactans", + "76": "tarantula", + "77": "wolf spider, hunting spider", + "78": "tick", + "79": "centipede", + "80": "black grouse", + "81": "ptarmigan", + "82": "ruffed grouse, partridge, Bonasa umbellus", + "83": "prairie chicken, prairie grouse, prairie fowl", + "84": "peacock", + "85": "quail", + "86": "partridge", + "87": "African grey, African gray, Psittacus erithacus", + "88": "macaw", + "89": "sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita", + "90": "lorikeet", + "91": "coucal", + "92": "bee eater", + "93": "hornbill", + "94": "hummingbird", + "95": "jacamar", + "96": "toucan", + "97": "drake", + "98": "red-breasted merganser, Mergus serrator", + "99": "goose", + "100": "black swan, Cygnus atratus", + "101": "tusker", + "102": "echidna, spiny anteater, anteater", + "103": "platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus", + "104": "wallaby, brush kangaroo", + "105": "koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus", + "106": "wombat", + "107": "jellyfish", + "108": "sea anemone, anemone", + "109": "brain coral", + "110": "flatworm, platyhelminth", + "111": "nematode, nematode worm, roundworm", + "112": "conch", + "113": "snail", + "114": "slug", + "115": "sea slug, nudibranch", + "116": "chiton, coat-of-mail shell, sea cradle, polyplacophore", + "117": "chambered nautilus, pearly nautilus, nautilus", + "118": "Dungeness crab, Cancer magister", + "119": "rock crab, Cancer irroratus", + "120": "fiddler crab", + "121": "king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica", + "122": "American lobster, Northern lobster, Maine lobster, Homarus americanus", + "123": "spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish", + "124": "crayfish, crawfish, crawdad, crawdaddy", + "125": "hermit crab", + "126": "isopod", + "127": "white stork, Ciconia ciconia", + "128": "black stork, Ciconia nigra", + "129": "spoonbill", + "130": "flamingo", + "131": "little blue heron, Egretta caerulea", + "132": "American egret, great white heron, Egretta albus", + "133": "bittern", + "134": "crane", + "135": "limpkin, Aramus pictus", + "136": "European gallinule, Porphyrio porphyrio", + "137": "American coot, marsh hen, mud hen, water hen, Fulica americana", + "138": "bustard", + "139": "ruddy turnstone, Arenaria interpres", + "140": "red-backed sandpiper, dunlin, Erolia alpina", + "141": "redshank, Tringa totanus", + "142": "dowitcher", + "143": "oystercatcher, oyster catcher", + "144": "pelican", + "145": "king penguin, Aptenodytes patagonica", + "146": "albatross, mollymawk", + "147": "grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus", + "148": "killer whale, killer, orca, grampus, sea wolf, Orcinus orca", + "149": "dugong, Dugong dugon", + "150": "sea lion", + "151": "Chihuahua", + "152": "Japanese spaniel", + "153": "Maltese dog, Maltese terrier, Maltese", + "154": "Pekinese, Pekingese, Peke", + "155": "Shih-Tzu", + "156": "Blenheim spaniel", + "157": "papillon", + "158": "toy terrier", + "159": "Rhodesian ridgeback", + "160": "Afghan hound, Afghan", + "161": "basset, basset hound", + "162": "beagle", + "163": "bloodhound, sleuthhound", + "164": "bluetick", + "165": "black-and-tan coonhound", + "166": "Walker hound, Walker foxhound", + "167": "English foxhound", + "168": "redbone", + "169": "borzoi, Russian wolfhound", + "170": "Irish wolfhound", + "171": "Italian greyhound", + "172": "whippet", + "173": "Ibizan hound, Ibizan Podenco", + "174": "Norwegian elkhound, elkhound", + "175": "otterhound, otter hound", + "176": "Saluki, gazelle hound", + "177": "Scottish deerhound, deerhound", + "178": "Weimaraner", + "179": "Staffordshire bullterrier, Staffordshire bull terrier", + "180": "American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier", + "181": "Bedlington terrier", + "182": "Border terrier", + "183": "Kerry blue terrier", + "184": "Irish terrier", + "185": "Norfolk terrier", + "186": "Norwich terrier", + "187": "Yorkshire terrier", + "188": "wire-haired fox terrier", + "189": "Lakeland terrier", + "190": "Sealyham terrier, Sealyham", + "191": "Airedale, Airedale terrier", + "192": "cairn, cairn terrier", + "193": "Australian terrier", + "194": "Dandie Dinmont, Dandie Dinmont terrier", + "195": "Boston bull, Boston terrier", + "196": "miniature schnauzer", + "197": "giant schnauzer", + "198": "standard schnauzer", + "199": "Scotch terrier, Scottish terrier, Scottie", + "200": "Tibetan terrier, chrysanthemum dog", + "201": "silky terrier, Sydney silky", + "202": "soft-coated wheaten terrier", + "203": "West Highland white terrier", + "204": "Lhasa, Lhasa apso", + "205": "flat-coated retriever", + "206": "curly-coated retriever", + "207": "golden retriever", + "208": "Labrador retriever", + "209": "Chesapeake Bay retriever", + "210": "German short-haired pointer", + "211": "vizsla, Hungarian pointer", + "212": "English setter", + "213": "Irish setter, red setter", + "214": "Gordon setter", + "215": "Brittany spaniel", + "216": "clumber, clumber spaniel", + "217": "English springer, English springer spaniel", + "218": "Welsh springer spaniel", + "219": "cocker spaniel, English cocker spaniel, cocker", + "220": "Sussex spaniel", + "221": "Irish water spaniel", + "222": "kuvasz", + "223": "schipperke", + "224": "groenendael", + "225": "malinois", + "226": "briard", + "227": "kelpie", + "228": "komondor", + "229": "Old English sheepdog, bobtail", + "230": "Shetland sheepdog, Shetland sheep dog, Shetland", + "231": "collie", + "232": "Border collie", + "233": "Bouvier des Flandres, Bouviers des Flandres", + "234": "Rottweiler", + "235": "German shepherd, German shepherd dog, German police dog, alsatian", + "236": "Doberman, Doberman pinscher", + "237": "miniature pinscher", + "238": "Greater Swiss Mountain dog", + "239": "Bernese mountain dog", + "240": "Appenzeller", + "241": "EntleBucher", + "242": "boxer", + "243": "bull mastiff", + "244": "Tibetan mastiff", + "245": "French bulldog", + "246": "Great Dane", + "247": "Saint Bernard, St Bernard", + "248": "Eskimo dog, husky", + "249": "malamute, malemute, Alaskan malamute", + "250": "Siberian husky", + "251": "dalmatian, coach dog, carriage dog", + "252": "affenpinscher, monkey pinscher, monkey dog", + "253": "basenji", + "254": "pug, pug-dog", + "255": "Leonberg", + "256": "Newfoundland, Newfoundland dog", + "257": "Great Pyrenees", + "258": "Samoyed, Samoyede", + "259": "Pomeranian", + "260": "chow, chow chow", + "261": "keeshond", + "262": "Brabancon griffon", + "263": "Pembroke, Pembroke Welsh corgi", + "264": "Cardigan, Cardigan Welsh corgi", + "265": "toy poodle", + "266": "miniature poodle", + "267": "standard poodle", + "268": "Mexican hairless", + "269": "timber wolf, grey wolf, gray wolf, Canis lupus", + "270": "white wolf, Arctic wolf, Canis lupus tundrarum", + "271": "red wolf, maned wolf, Canis rufus, Canis niger", + "272": "coyote, prairie wolf, brush wolf, Canis latrans", + "273": "dingo, warrigal, warragal, Canis dingo", + "274": "dhole, Cuon alpinus", + "275": "African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus", + "276": "hyena, hyaena", + "277": "red fox, Vulpes vulpes", + "278": "kit fox, Vulpes macrotis", + "279": "Arctic fox, white fox, Alopex lagopus", + "280": "grey fox, gray fox, Urocyon cinereoargenteus", + "281": "tabby, tabby cat", + "282": "tiger cat", + "283": "Persian cat", + "284": "Siamese cat, Siamese", + "285": "Egyptian cat", + "286": "cougar, puma, catamount, mountain lion, painter, panther, Felis concolor", + "287": "lynx, catamount", + "288": "leopard, Panthera pardus", + "289": "snow leopard, ounce, Panthera uncia", + "290": "jaguar, panther, Panthera onca, Felis onca", + "291": "lion, king of beasts, Panthera leo", + "292": "tiger, Panthera tigris", + "293": "cheetah, chetah, Acinonyx jubatus", + "294": "brown bear, bruin, Ursus arctos", + "295": "American black bear, black bear, Ursus americanus, Euarctos americanus", + "296": "ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus", + "297": "sloth bear, Melursus ursinus, Ursus ursinus", + "298": "mongoose", + "299": "meerkat, mierkat", + "300": "tiger beetle", + "301": "ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle", + "302": "ground beetle, carabid beetle", + "303": "long-horned beetle, longicorn, longicorn beetle", + "304": "leaf beetle, chrysomelid", + "305": "dung beetle", + "306": "rhinoceros beetle", + "307": "weevil", + "308": "fly", + "309": "bee", + "310": "ant, emmet, pismire", + "311": "grasshopper, hopper", + "312": "cricket", + "313": "walking stick, walkingstick, stick insect", + "314": "cockroach, roach", + "315": "mantis, mantid", + "316": "cicada, cicala", + "317": "leafhopper", + "318": "lacewing, lacewing fly", + "319": "dragonfly, darning needle, devil's darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk", + "320": "damselfly", + "321": "admiral", + "322": "ringlet, ringlet butterfly", + "323": "monarch, monarch butterfly, milkweed butterfly, Danaus plexippus", + "324": "cabbage butterfly", + "325": "sulphur butterfly, sulfur butterfly", + "326": "lycaenid, lycaenid butterfly", + "327": "starfish, sea star", + "328": "sea urchin", + "329": "sea cucumber, holothurian", + "330": "wood rabbit, cottontail, cottontail rabbit", + "331": "hare", + "332": "Angora, Angora rabbit", + "333": "hamster", + "334": "porcupine, hedgehog", + "335": "fox squirrel, eastern fox squirrel, Sciurus niger", + "336": "marmot", + "337": "beaver", + "338": "guinea pig, Cavia cobaya", + "339": "sorrel", + "340": "zebra", + "341": "hog, pig, grunter, squealer, Sus scrofa", + "342": "wild boar, boar, Sus scrofa", + "343": "warthog", + "344": "hippopotamus, hippo, river horse, Hippopotamus amphibius", + "345": "ox", + "346": "water buffalo, water ox, Asiatic buffalo, Bubalus bubalis", + "347": "bison", + "348": "ram, tup", + "349": "bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis", + "350": "ibex, Capra ibex", + "351": "hartebeest", + "352": "impala, Aepyceros melampus", + "353": "gazelle", + "354": "Arabian camel, dromedary, Camelus dromedarius", + "355": "llama", + "356": "weasel", + "357": "mink", + "358": "polecat, fitch, foulmart, foumart, Mustela putorius", + "359": "black-footed ferret, ferret, Mustela nigripes", + "360": "otter", + "361": "skunk, polecat, wood pussy", + "362": "badger", + "363": "armadillo", + "364": "three-toed sloth, ai, Bradypus tridactylus", + "365": "orangutan, orang, orangutang, Pongo pygmaeus", + "366": "gorilla, Gorilla gorilla", + "367": "chimpanzee, chimp, Pan troglodytes", + "368": "gibbon, Hylobates lar", + "369": "siamang, Hylobates syndactylus, Symphalangus syndactylus", + "370": "guenon, guenon monkey", + "371": "patas, hussar monkey, Erythrocebus patas", + "372": "baboon", + "373": "macaque", + "374": "langur", + "375": "colobus, colobus monkey", + "376": "proboscis monkey, Nasalis larvatus", + "377": "marmoset", + "378": "capuchin, ringtail, Cebus capucinus", + "379": "howler monkey, howler", + "380": "titi, titi monkey", + "381": "spider monkey, Ateles geoffroyi", + "382": "squirrel monkey, Saimiri sciureus", + "383": "Madagascar cat, ring-tailed lemur, Lemur catta", + "384": "indri, indris, Indri indri, Indri brevicaudatus", + "385": "Indian elephant, Elephas maximus", + "386": "African elephant, Loxodonta africana", + "387": "lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens", + "388": "giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca", + "389": "barracouta, snoek", + "390": "eel", + "391": "coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch", + "392": "rock beauty, Holocanthus tricolor", + "393": "anemone fish", + "394": "sturgeon", + "395": "gar, garfish, garpike, billfish, Lepisosteus osseus", + "396": "lionfish", + "397": "puffer, pufferfish, blowfish, globefish", + "398": "abacus", + "399": "abaya", + "400": "academic gown, academic robe, judge's robe", + "401": "accordion, piano accordion, squeeze box", + "402": "acoustic guitar", + "403": "aircraft carrier, carrier, flattop, attack aircraft carrier", + "404": "airliner", + "405": "airship, dirigible", + "406": "altar", + "407": "ambulance", + "408": "amphibian, amphibious vehicle", + "409": "analog clock", + "410": "apiary, bee house", + "411": "apron", + "412": "ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin", + "413": "assault rifle, assault gun", + "414": "backpack, back pack, knapsack, packsack, rucksack, haversack", + "415": "bakery, bakeshop, bakehouse", + "416": "balance beam, beam", + "417": "balloon", + "418": "ballpoint, ballpoint pen, ballpen, Biro", + "419": "Band Aid", + "420": "banjo", + "421": "bannister, banister, balustrade, balusters, handrail", + "422": "barbell", + "423": "barber chair", + "424": "barbershop", + "425": "barn", + "426": "barometer", + "427": "barrel, cask", + "428": "barrow, garden cart, lawn cart, wheelbarrow", + "429": "baseball", + "430": "basketball", + "431": "bassinet", + "432": "bassoon", + "433": "bathing cap, swimming cap", + "434": "bath towel", + "435": "bathtub, bathing tub, bath, tub", + "436": "beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon", + "437": "beacon, lighthouse, beacon light, pharos", + "438": "beaker", + "439": "bearskin, busby, shako", + "440": "beer bottle", + "441": "beer glass", + "442": "bell cote, bell cot", + "443": "bib", + "444": "bicycle-built-for-two, tandem bicycle, tandem", + "445": "bikini, two-piece", + "446": "binder, ring-binder", + "447": "binoculars, field glasses, opera glasses", + "448": "birdhouse", + "449": "boathouse", + "450": "bobsled, bobsleigh, bob", + "451": "bolo tie, bolo, bola tie, bola", + "452": "bonnet, poke bonnet", + "453": "bookcase", + "454": "bookshop, bookstore, bookstall", + "455": "bottlecap", + "456": "bow", + "457": "bow tie, bow-tie, bowtie", + "458": "brass, memorial tablet, plaque", + "459": "brassiere, bra, bandeau", + "460": "breakwater, groin, groyne, mole, bulwark, seawall, jetty", + "461": "breastplate, aegis, egis", + "462": "broom", + "463": "bucket, pail", + "464": "buckle", + "465": "bulletproof vest", + "466": "bullet train, bullet", + "467": "butcher shop, meat market", + "468": "cab, hack, taxi, taxicab", + "469": "caldron, cauldron", + "470": "candle, taper, wax light", + "471": "cannon", + "472": "canoe", + "473": "can opener, tin opener", + "474": "cardigan", + "475": "car mirror", + "476": "carousel, carrousel, merry-go-round, roundabout, whirligig", + "477": "carpenter's kit, tool kit", + "478": "carton", + "479": "car wheel", + "480": "cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM", + "481": "cassette", + "482": "cassette player", + "483": "castle", + "484": "catamaran", + "485": "CD player", + "486": "cello, violoncello", + "487": "cellular telephone, cellular phone, cellphone, cell, mobile phone", + "488": "chain", + "489": "chainlink fence", + "490": "chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour", + "491": "chain saw, chainsaw", + "492": "chest", + "493": "chiffonier, commode", + "494": "chime, bell, gong", + "495": "china cabinet, china closet", + "496": "Christmas stocking", + "497": "church, church building", + "498": "cinema, movie theater, movie theatre, movie house, picture palace", + "499": "cleaver, meat cleaver, chopper", + "500": "cliff dwelling", + "501": "cloak", + "502": "clog, geta, patten, sabot", + "503": "cocktail shaker", + "504": "coffee mug", + "505": "coffeepot", + "506": "coil, spiral, volute, whorl, helix", + "507": "combination lock", + "508": "computer keyboard, keypad", + "509": "confectionery, confectionary, candy store", + "510": "container ship, containership, container vessel", + "511": "convertible", + "512": "corkscrew, bottle screw", + "513": "cornet, horn, trumpet, trump", + "514": "cowboy boot", + "515": "cowboy hat, ten-gallon hat", + "516": "cradle", + "517": "crane", + "518": "crash helmet", + "519": "crate", + "520": "crib, cot", + "521": "Crock Pot", + "522": "croquet ball", + "523": "crutch", + "524": "cuirass", + "525": "dam, dike, dyke", + "526": "desk", + "527": "desktop computer", + "528": "dial telephone, dial phone", + "529": "diaper, nappy, napkin", + "530": "digital clock", + "531": "digital watch", + "532": "dining table, board", + "533": "dishrag, dishcloth", + "534": "dishwasher, dish washer, dishwashing machine", + "535": "disk brake, disc brake", + "536": "dock, dockage, docking facility", + "537": "dogsled, dog sled, dog sleigh", + "538": "dome", + "539": "doormat, welcome mat", + "540": "drilling platform, offshore rig", + "541": "drum, membranophone, tympan", + "542": "drumstick", + "543": "dumbbell", + "544": "Dutch oven", + "545": "electric fan, blower", + "546": "electric guitar", + "547": "electric locomotive", + "548": "entertainment center", + "549": "envelope", + "550": "espresso maker", + "551": "face powder", + "552": "feather boa, boa", + "553": "file, file cabinet, filing cabinet", + "554": "fireboat", + "555": "fire engine, fire truck", + "556": "fire screen, fireguard", + "557": "flagpole, flagstaff", + "558": "flute, transverse flute", + "559": "folding chair", + "560": "football helmet", + "561": "forklift", + "562": "fountain", + "563": "fountain pen", + "564": "four-poster", + "565": "freight car", + "566": "French horn, horn", + "567": "frying pan, frypan, skillet", + "568": "fur coat", + "569": "garbage truck, dustcart", + "570": "gasmask, respirator, gas helmet", + "571": "gas pump, gasoline pump, petrol pump, island dispenser", + "572": "goblet", + "573": "go-kart", + "574": "golf ball", + "575": "golfcart, golf cart", + "576": "gondola", + "577": "gong, tam-tam", + "578": "gown", + "579": "grand piano, grand", + "580": "greenhouse, nursery, glasshouse", + "581": "grille, radiator grille", + "582": "grocery store, grocery, food market, market", + "583": "guillotine", + "584": "hair slide", + "585": "hair spray", + "586": "half track", + "587": "hammer", + "588": "hamper", + "589": "hand blower, blow dryer, blow drier, hair dryer, hair drier", + "590": "hand-held computer, hand-held microcomputer", + "591": "handkerchief, hankie, hanky, hankey", + "592": "hard disc, hard disk, fixed disk", + "593": "harmonica, mouth organ, harp, mouth harp", + "594": "harp", + "595": "harvester, reaper", + "596": "hatchet", + "597": "holster", + "598": "home theater, home theatre", + "599": "honeycomb", + "600": "hook, claw", + "601": "hoopskirt, crinoline", + "602": "horizontal bar, high bar", + "603": "horse cart, horse-cart", + "604": "hourglass", + "605": "iPod", + "606": "iron, smoothing iron", + "607": "jack-o'-lantern", + "608": "jean, blue jean, denim", + "609": "jeep, landrover", + "610": "jersey, T-shirt, tee shirt", + "611": "jigsaw puzzle", + "612": "jinrikisha, ricksha, rickshaw", + "613": "joystick", + "614": "kimono", + "615": "knee pad", + "616": "knot", + "617": "lab coat, laboratory coat", + "618": "ladle", + "619": "lampshade, lamp shade", + "620": "laptop, laptop computer", + "621": "lawn mower, mower", + "622": "lens cap, lens cover", + "623": "letter opener, paper knife, paperknife", + "624": "library", + "625": "lifeboat", + "626": "lighter, light, igniter, ignitor", + "627": "limousine, limo", + "628": "liner, ocean liner", + "629": "lipstick, lip rouge", + "630": "Loafer", + "631": "lotion", + "632": "loudspeaker, speaker, speaker unit, loudspeaker system, speaker system", + "633": "loupe, jeweler's loupe", + "634": "lumbermill, sawmill", + "635": "magnetic compass", + "636": "mailbag, postbag", + "637": "mailbox, letter box", + "638": "maillot", + "639": "maillot, tank suit", + "640": "manhole cover", + "641": "maraca", + "642": "marimba, xylophone", + "643": "mask", + "644": "matchstick", + "645": "maypole", + "646": "maze, labyrinth", + "647": "measuring cup", + "648": "medicine chest, medicine cabinet", + "649": "megalith, megalithic structure", + "650": "microphone, mike", + "651": "microwave, microwave oven", + "652": "military uniform", + "653": "milk can", + "654": "minibus", + "655": "miniskirt, mini", + "656": "minivan", + "657": "missile", + "658": "mitten", + "659": "mixing bowl", + "660": "mobile home, manufactured home", + "661": "Model T", + "662": "modem", + "663": "monastery", + "664": "monitor", + "665": "moped", + "666": "mortar", + "667": "mortarboard", + "668": "mosque", + "669": "mosquito net", + "670": "motor scooter, scooter", + "671": "mountain bike, all-terrain bike, off-roader", + "672": "mountain tent", + "673": "mouse, computer mouse", + "674": "mousetrap", + "675": "moving van", + "676": "muzzle", + "677": "nail", + "678": "neck brace", + "679": "necklace", + "680": "nipple", + "681": "notebook, notebook computer", + "682": "obelisk", + "683": "oboe, hautboy, hautbois", + "684": "ocarina, sweet potato", + "685": "odometer, hodometer, mileometer, milometer", + "686": "oil filter", + "687": "organ, pipe organ", + "688": "oscilloscope, scope, cathode-ray oscilloscope, CRO", + "689": "overskirt", + "690": "oxcart", + "691": "oxygen mask", + "692": "packet", + "693": "paddle, boat paddle", + "694": "paddlewheel, paddle wheel", + "695": "padlock", + "696": "paintbrush", + "697": "pajama, pyjama, pj's, jammies", + "698": "palace", + "699": "panpipe, pandean pipe, syrinx", + "700": "paper towel", + "701": "parachute, chute", + "702": "parallel bars, bars", + "703": "park bench", + "704": "parking meter", + "705": "passenger car, coach, carriage", + "706": "patio, terrace", + "707": "pay-phone, pay-station", + "708": "pedestal, plinth, footstall", + "709": "pencil box, pencil case", + "710": "pencil sharpener", + "711": "perfume, essence", + "712": "Petri dish", + "713": "photocopier", + "714": "pick, plectrum, plectron", + "715": "pickelhaube", + "716": "picket fence, paling", + "717": "pickup, pickup truck", + "718": "pier", + "719": "piggy bank, penny bank", + "720": "pill bottle", + "721": "pillow", + "722": "ping-pong ball", + "723": "pinwheel", + "724": "pirate, pirate ship", + "725": "pitcher, ewer", + "726": "plane, carpenter's plane, woodworking plane", + "727": "planetarium", + "728": "plastic bag", + "729": "plate rack", + "730": "plow, plough", + "731": "plunger, plumber's helper", + "732": "Polaroid camera, Polaroid Land camera", + "733": "pole", + "734": "police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria", + "735": "poncho", + "736": "pool table, billiard table, snooker table", + "737": "pop bottle, soda bottle", + "738": "pot, flowerpot", + "739": "potter's wheel", + "740": "power drill", + "741": "prayer rug, prayer mat", + "742": "printer", + "743": "prison, prison house", + "744": "projectile, missile", + "745": "projector", + "746": "puck, hockey puck", + "747": "punching bag, punch bag, punching ball, punchball", + "748": "purse", + "749": "quill, quill pen", + "750": "quilt, comforter, comfort, puff", + "751": "racer, race car, racing car", + "752": "racket, racquet", + "753": "radiator", + "754": "radio, wireless", + "755": "radio telescope, radio reflector", + "756": "rain barrel", + "757": "recreational vehicle, RV, R.V.", + "758": "reel", + "759": "reflex camera", + "760": "refrigerator, icebox", + "761": "remote control, remote", + "762": "restaurant, eating house, eating place, eatery", + "763": "revolver, six-gun, six-shooter", + "764": "rifle", + "765": "rocking chair, rocker", + "766": "rotisserie", + "767": "rubber eraser, rubber, pencil eraser", + "768": "rugby ball", + "769": "rule, ruler", + "770": "running shoe", + "771": "safe", + "772": "safety pin", + "773": "saltshaker, salt shaker", + "774": "sandal", + "775": "sarong", + "776": "sax, saxophone", + "777": "scabbard", + "778": "scale, weighing machine", + "779": "school bus", + "780": "schooner", + "781": "scoreboard", + "782": "screen, CRT screen", + "783": "screw", + "784": "screwdriver", + "785": "seat belt, seatbelt", + "786": "sewing machine", + "787": "shield, buckler", + "788": "shoe shop, shoe-shop, shoe store", + "789": "shoji", + "790": "shopping basket", + "791": "shopping cart", + "792": "shovel", + "793": "shower cap", + "794": "shower curtain", + "795": "ski", + "796": "ski mask", + "797": "sleeping bag", + "798": "slide rule, slipstick", + "799": "sliding door", + "800": "slot, one-armed bandit", + "801": "snorkel", + "802": "snowmobile", + "803": "snowplow, snowplough", + "804": "soap dispenser", + "805": "soccer ball", + "806": "sock", + "807": "solar dish, solar collector, solar furnace", + "808": "sombrero", + "809": "soup bowl", + "810": "space bar", + "811": "space heater", + "812": "space shuttle", + "813": "spatula", + "814": "speedboat", + "815": "spider web, spider's web", + "816": "spindle", + "817": "sports car, sport car", + "818": "spotlight, spot", + "819": "stage", + "820": "steam locomotive", + "821": "steel arch bridge", + "822": "steel drum", + "823": "stethoscope", + "824": "stole", + "825": "stone wall", + "826": "stopwatch, stop watch", + "827": "stove", + "828": "strainer", + "829": "streetcar, tram, tramcar, trolley, trolley car", + "830": "stretcher", + "831": "studio couch, day bed", + "832": "stupa, tope", + "833": "submarine, pigboat, sub, U-boat", + "834": "suit, suit of clothes", + "835": "sundial", + "836": "sunglass", + "837": "sunglasses, dark glasses, shades", + "838": "sunscreen, sunblock, sun blocker", + "839": "suspension bridge", + "840": "swab, swob, mop", + "841": "sweatshirt", + "842": "swimming trunks, bathing trunks", + "843": "swing", + "844": "switch, electric switch, electrical switch", + "845": "syringe", + "846": "table lamp", + "847": "tank, army tank, armored combat vehicle, armoured combat vehicle", + "848": "tape player", + "849": "teapot", + "850": "teddy, teddy bear", + "851": "television, television system", + "852": "tennis ball", + "853": "thatch, thatched roof", + "854": "theater curtain, theatre curtain", + "855": "thimble", + "856": "thresher, thrasher, threshing machine", + "857": "throne", + "858": "tile roof", + "859": "toaster", + "860": "tobacco shop, tobacconist shop, tobacconist", + "861": "toilet seat", + "862": "torch", + "863": "totem pole", + "864": "tow truck, tow car, wrecker", + "865": "toyshop", + "866": "tractor", + "867": "trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi", + "868": "tray", + "869": "trench coat", + "870": "tricycle, trike, velocipede", + "871": "trimaran", + "872": "tripod", + "873": "triumphal arch", + "874": "trolleybus, trolley coach, trackless trolley", + "875": "trombone", + "876": "tub, vat", + "877": "turnstile", + "878": "typewriter keyboard", + "879": "umbrella", + "880": "unicycle, monocycle", + "881": "upright, upright piano", + "882": "vacuum, vacuum cleaner", + "883": "vase", + "884": "vault", + "885": "velvet", + "886": "vending machine", + "887": "vestment", + "888": "viaduct", + "889": "violin, fiddle", + "890": "volleyball", + "891": "waffle iron", + "892": "wall clock", + "893": "wallet, billfold, notecase, pocketbook", + "894": "wardrobe, closet, press", + "895": "warplane, military plane", + "896": "washbasin, handbasin, washbowl, lavabo, wash-hand basin", + "897": "washer, automatic washer, washing machine", + "898": "water bottle", + "899": "water jug", + "900": "water tower", + "901": "whiskey jug", + "902": "whistle", + "903": "wig", + "904": "window screen", + "905": "window shade", + "906": "Windsor tie", + "907": "wine bottle", + "908": "wing", + "909": "wok", + "910": "wooden spoon", + "911": "wool, woolen, woollen", + "912": "worm fence, snake fence, snake-rail fence, Virginia fence", + "913": "wreck", + "914": "yawl", + "915": "yurt", + "916": "web site, website, internet site, site", + "917": "comic book", + "918": "crossword puzzle, crossword", + "919": "street sign", + "920": "traffic light, traffic signal, stoplight", + "921": "book jacket, dust cover, dust jacket, dust wrapper", + "922": "menu", + "923": "plate", + "924": "guacamole", + "925": "consomme", + "926": "hot pot, hotpot", + "927": "trifle", + "928": "ice cream, icecream", + "929": "ice lolly, lolly, lollipop, popsicle", + "930": "French loaf", + "931": "bagel, beigel", + "932": "pretzel", + "933": "cheeseburger", + "934": "hotdog, hot dog, red hot", + "935": "mashed potato", + "936": "head cabbage", + "937": "broccoli", + "938": "cauliflower", + "939": "zucchini, courgette", + "940": "spaghetti squash", + "941": "acorn squash", + "942": "butternut squash", + "943": "cucumber, cuke", + "944": "artichoke, globe artichoke", + "945": "bell pepper", + "946": "cardoon", + "947": "mushroom", + "948": "Granny Smith", + "949": "strawberry", + "950": "orange", + "951": "lemon", + "952": "fig", + "953": "pineapple, ananas", + "954": "banana", + "955": "jackfruit, jak, jack", + "956": "custard apple", + "957": "pomegranate", + "958": "hay", + "959": "carbonara", + "960": "chocolate sauce, chocolate syrup", + "961": "dough", + "962": "meat loaf, meatloaf", + "963": "pizza, pizza pie", + "964": "potpie", + "965": "burrito", + "966": "red wine", + "967": "espresso", + "968": "cup", + "969": "eggnog", + "970": "alp", + "971": "bubble", + "972": "cliff, drop, drop-off", + "973": "coral reef", + "974": "geyser", + "975": "lakeside, lakeshore", + "976": "promontory, headland, head, foreland", + "977": "sandbar, sand bar", + "978": "seashore, coast, seacoast, sea-coast", + "979": "valley, vale", + "980": "volcano", + "981": "ballplayer, baseball player", + "982": "groom, bridegroom", + "983": "scuba diver", + "984": "rapeseed", + "985": "daisy", + "986": "yellow lady's slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum", + "987": "corn", + "988": "acorn", + "989": "hip, rose hip, rosehip", + "990": "buckeye, horse chestnut, conker", + "991": "coral fungus", + "992": "agaric", + "993": "gyromitra", + "994": "stinkhorn, carrion fungus", + "995": "earthstar", + "996": "hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa", + "997": "bolete", + "998": "ear, spike, capitulum", + "999": "toilet tissue, toilet paper, bathroom tissue" + }, + "image_size": 256, + "initializer_range": 0.02, + "label2id": { + "Afghan hound, Afghan": 160, + "African chameleon, Chamaeleo chamaeleon": 47, + "African crocodile, Nile crocodile, Crocodylus niloticus": 49, + "African elephant, Loxodonta africana": 386, + "African grey, African gray, Psittacus erithacus": 87, + "African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus": 275, + "Airedale, Airedale terrier": 191, + "American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier": 180, + "American alligator, Alligator mississipiensis": 50, + "American black bear, black bear, Ursus americanus, Euarctos americanus": 295, + "American chameleon, anole, Anolis carolinensis": 40, + "American coot, marsh hen, mud hen, water hen, Fulica americana": 137, + "American egret, great white heron, Egretta albus": 132, + "American lobster, Northern lobster, Maine lobster, Homarus americanus": 122, + "Angora, Angora rabbit": 332, + "Appenzeller": 240, + "Arabian camel, dromedary, Camelus dromedarius": 354, + "Arctic fox, white fox, Alopex lagopus": 279, + "Australian terrier": 193, + "Band Aid": 419, + "Bedlington terrier": 181, + "Bernese mountain dog": 239, + "Blenheim spaniel": 156, + "Border collie": 232, + "Border terrier": 182, + "Boston bull, Boston terrier": 195, + "Bouvier des Flandres, Bouviers des Flandres": 233, + "Brabancon griffon": 262, + "Brittany spaniel": 215, + "CD player": 485, + "Cardigan, Cardigan Welsh corgi": 264, + "Chesapeake Bay retriever": 209, + "Chihuahua": 151, + "Christmas stocking": 496, + "Crock Pot": 521, + "Dandie Dinmont, Dandie Dinmont terrier": 194, + "Doberman, Doberman pinscher": 236, + "Dungeness crab, Cancer magister": 118, + "Dutch oven": 544, + "Egyptian cat": 285, + "English foxhound": 167, + "English setter": 212, + "English springer, English springer spaniel": 217, + "EntleBucher": 241, + "Eskimo dog, husky": 248, + "European fire salamander, Salamandra salamandra": 25, + "European gallinule, Porphyrio porphyrio": 136, + "French bulldog": 245, + "French horn, horn": 566, + "French loaf": 930, + "German shepherd, German shepherd dog, German police dog, alsatian": 235, + "German short-haired pointer": 210, + "Gila monster, Heloderma suspectum": 45, + "Gordon setter": 214, + "Granny Smith": 948, + "Great Dane": 246, + "Great Pyrenees": 257, + "Greater Swiss Mountain dog": 238, + "Ibizan hound, Ibizan Podenco": 173, + "Indian cobra, Naja naja": 63, + "Indian elephant, Elephas maximus": 385, + "Irish setter, red setter": 213, + "Irish terrier": 184, + "Irish water spaniel": 221, + "Irish wolfhound": 170, + "Italian greyhound": 171, + "Japanese spaniel": 152, + "Kerry blue terrier": 183, + "Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis": 48, + "Labrador retriever": 208, + "Lakeland terrier": 189, + "Leonberg": 255, + "Lhasa, Lhasa apso": 204, + "Loafer": 630, + "Madagascar cat, ring-tailed lemur, Lemur catta": 383, + "Maltese dog, Maltese terrier, Maltese": 153, + "Mexican hairless": 268, + "Model T": 661, + "Newfoundland, Newfoundland dog": 256, + "Norfolk terrier": 185, + "Norwegian elkhound, elkhound": 174, + "Norwich terrier": 186, + "Old English sheepdog, bobtail": 229, + "Pekinese, Pekingese, Peke": 154, + "Pembroke, Pembroke Welsh corgi": 263, + "Persian cat": 283, + "Petri dish": 712, + "Polaroid camera, Polaroid Land camera": 732, + "Pomeranian": 259, + "Rhodesian ridgeback": 159, + "Rottweiler": 234, + "Saint Bernard, St Bernard": 247, + "Saluki, gazelle hound": 176, + "Samoyed, Samoyede": 258, + "Scotch terrier, Scottish terrier, Scottie": 199, + "Scottish deerhound, deerhound": 177, + "Sealyham terrier, Sealyham": 190, + "Shetland sheepdog, Shetland sheep dog, Shetland": 230, + "Shih-Tzu": 155, + "Siamese cat, Siamese": 284, + "Siberian husky": 250, + "Staffordshire bullterrier, Staffordshire bull terrier": 179, + "Sussex spaniel": 220, + "Tibetan mastiff": 244, + "Tibetan terrier, chrysanthemum dog": 200, + "Walker hound, Walker foxhound": 166, + "Weimaraner": 178, + "Welsh springer spaniel": 218, + "West Highland white terrier": 203, + "Windsor tie": 906, + "Yorkshire terrier": 187, + "abacus": 398, + "abaya": 399, + "academic gown, academic robe, judge's robe": 400, + "accordion, piano accordion, squeeze box": 401, + "acorn": 988, + "acorn squash": 941, + "acoustic guitar": 402, + "admiral": 321, + "affenpinscher, monkey pinscher, monkey dog": 252, + "agama": 42, + "agaric": 992, + "aircraft carrier, carrier, flattop, attack aircraft carrier": 403, + "airliner": 404, + "airship, dirigible": 405, + "albatross, mollymawk": 146, + "alligator lizard": 44, + "alp": 970, + "altar": 406, + "ambulance": 407, + "amphibian, amphibious vehicle": 408, + "analog clock": 409, + "anemone fish": 393, + "ant, emmet, pismire": 310, + "apiary, bee house": 410, + "apron": 411, + "armadillo": 363, + "artichoke, globe artichoke": 944, + "ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin": 412, + "assault rifle, assault gun": 413, + "axolotl, mud puppy, Ambystoma mexicanum": 29, + "baboon": 372, + "backpack, back pack, knapsack, packsack, rucksack, haversack": 414, + "badger": 362, + "bagel, beigel": 931, + "bakery, bakeshop, bakehouse": 415, + "balance beam, beam": 416, + "bald eagle, American eagle, Haliaeetus leucocephalus": 22, + "balloon": 417, + "ballplayer, baseball player": 981, + "ballpoint, ballpoint pen, ballpen, Biro": 418, + "banana": 954, + "banded gecko": 38, + "banjo": 420, + "bannister, banister, balustrade, balusters, handrail": 421, + "barbell": 422, + "barber chair": 423, + "barbershop": 424, + "barn": 425, + "barn spider, Araneus cavaticus": 73, + "barometer": 426, + "barracouta, snoek": 389, + "barrel, cask": 427, + "barrow, garden cart, lawn cart, wheelbarrow": 428, + "baseball": 429, + "basenji": 253, + "basketball": 430, + "basset, basset hound": 161, + "bassinet": 431, + "bassoon": 432, + "bath towel": 434, + "bathing cap, swimming cap": 433, + "bathtub, bathing tub, bath, tub": 435, + "beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon": 436, + "beacon, lighthouse, beacon light, pharos": 437, + "beagle": 162, + "beaker": 438, + "bearskin, busby, shako": 439, + "beaver": 337, + "bee": 309, + "bee eater": 92, + "beer bottle": 440, + "beer glass": 441, + "bell cote, bell cot": 442, + "bell pepper": 945, + "bib": 443, + "bicycle-built-for-two, tandem bicycle, tandem": 444, + "bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis": 349, + "bikini, two-piece": 445, + "binder, ring-binder": 446, + "binoculars, field glasses, opera glasses": 447, + "birdhouse": 448, + "bison": 347, + "bittern": 133, + "black and gold garden spider, Argiope aurantia": 72, + "black grouse": 80, + "black stork, Ciconia nigra": 128, + "black swan, Cygnus atratus": 100, + "black widow, Latrodectus mactans": 75, + "black-and-tan coonhound": 165, + "black-footed ferret, ferret, Mustela nigripes": 359, + "bloodhound, sleuthhound": 163, + "bluetick": 164, + "boa constrictor, Constrictor constrictor": 61, + "boathouse": 449, + "bobsled, bobsleigh, bob": 450, + "bolete": 997, + "bolo tie, bolo, bola tie, bola": 451, + "bonnet, poke bonnet": 452, + "book jacket, dust cover, dust jacket, dust wrapper": 921, + "bookcase": 453, + "bookshop, bookstore, bookstall": 454, + "borzoi, Russian wolfhound": 169, + "bottlecap": 455, + "bow": 456, + "bow tie, bow-tie, bowtie": 457, + "box turtle, box tortoise": 37, + "boxer": 242, + "brain coral": 109, + "brambling, Fringilla montifringilla": 10, + "brass, memorial tablet, plaque": 458, + "brassiere, bra, bandeau": 459, + "breakwater, groin, groyne, mole, bulwark, seawall, jetty": 460, + "breastplate, aegis, egis": 461, + "briard": 226, + "broccoli": 937, + "broom": 462, + "brown bear, bruin, Ursus arctos": 294, + "bubble": 971, + "bucket, pail": 463, + "buckeye, horse chestnut, conker": 990, + "buckle": 464, + "bulbul": 16, + "bull mastiff": 243, + "bullet train, bullet": 466, + "bulletproof vest": 465, + "bullfrog, Rana catesbeiana": 30, + "burrito": 965, + "bustard": 138, + "butcher shop, meat market": 467, + "butternut squash": 942, + "cab, hack, taxi, taxicab": 468, + "cabbage butterfly": 324, + "cairn, cairn terrier": 192, + "caldron, cauldron": 469, + "can opener, tin opener": 473, + "candle, taper, wax light": 470, + "cannon": 471, + "canoe": 472, + "capuchin, ringtail, Cebus capucinus": 378, + "car mirror": 475, + "car wheel": 479, + "carbonara": 959, + "cardigan": 474, + "cardoon": 946, + "carousel, carrousel, merry-go-round, roundabout, whirligig": 476, + "carpenter's kit, tool kit": 477, + "carton": 478, + "cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM": 480, + "cassette": 481, + "cassette player": 482, + "castle": 483, + "catamaran": 484, + "cauliflower": 938, + "cello, violoncello": 486, + "cellular telephone, cellular phone, cellphone, cell, mobile phone": 487, + "centipede": 79, + "chain": 488, + "chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour": 490, + "chain saw, chainsaw": 491, + "chainlink fence": 489, + "chambered nautilus, pearly nautilus, nautilus": 117, + "cheeseburger": 933, + "cheetah, chetah, Acinonyx jubatus": 293, + "chest": 492, + "chickadee": 19, + "chiffonier, commode": 493, + "chime, bell, gong": 494, + "chimpanzee, chimp, Pan troglodytes": 367, + "china cabinet, china closet": 495, + "chiton, coat-of-mail shell, sea cradle, polyplacophore": 116, + "chocolate sauce, chocolate syrup": 960, + "chow, chow chow": 260, + "church, church building": 497, + "cicada, cicala": 316, + "cinema, movie theater, movie theatre, movie house, picture palace": 498, + "cleaver, meat cleaver, chopper": 499, + "cliff dwelling": 500, + "cliff, drop, drop-off": 972, + "cloak": 501, + "clog, geta, patten, sabot": 502, + "clumber, clumber spaniel": 216, + "cock": 7, + "cocker spaniel, English cocker spaniel, cocker": 219, + "cockroach, roach": 314, + "cocktail shaker": 503, + "coffee mug": 504, + "coffeepot": 505, + "coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch": 391, + "coil, spiral, volute, whorl, helix": 506, + "collie": 231, + "colobus, colobus monkey": 375, + "combination lock": 507, + "comic book": 917, + "common iguana, iguana, Iguana iguana": 39, + "common newt, Triturus vulgaris": 26, + "computer keyboard, keypad": 508, + "conch": 112, + "confectionery, confectionary, candy store": 509, + "consomme": 925, + "container ship, containership, container vessel": 510, + "convertible": 511, + "coral fungus": 991, + "coral reef": 973, + "corkscrew, bottle screw": 512, + "corn": 987, + "cornet, horn, trumpet, trump": 513, + "coucal": 91, + "cougar, puma, catamount, mountain lion, painter, panther, Felis concolor": 286, + "cowboy boot": 514, + "cowboy hat, ten-gallon hat": 515, + "coyote, prairie wolf, brush wolf, Canis latrans": 272, + "cradle": 516, + "crane": 517, + "crash helmet": 518, + "crate": 519, + "crayfish, crawfish, crawdad, crawdaddy": 124, + "crib, cot": 520, + "cricket": 312, + "croquet ball": 522, + "crossword puzzle, crossword": 918, + "crutch": 523, + "cucumber, cuke": 943, + "cuirass": 524, + "cup": 968, + "curly-coated retriever": 206, + "custard apple": 956, + "daisy": 985, + "dalmatian, coach dog, carriage dog": 251, + "dam, dike, dyke": 525, + "damselfly": 320, + "desk": 526, + "desktop computer": 527, + "dhole, Cuon alpinus": 274, + "dial telephone, dial phone": 528, + "diamondback, diamondback rattlesnake, Crotalus adamanteus": 67, + "diaper, nappy, napkin": 529, + "digital clock": 530, + "digital watch": 531, + "dingo, warrigal, warragal, Canis dingo": 273, + "dining table, board": 532, + "dishrag, dishcloth": 533, + "dishwasher, dish washer, dishwashing machine": 534, + "disk brake, disc brake": 535, + "dock, dockage, docking facility": 536, + "dogsled, dog sled, dog sleigh": 537, + "dome": 538, + "doormat, welcome mat": 539, + "dough": 961, + "dowitcher": 142, + "dragonfly, darning needle, devil's darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk": 319, + "drake": 97, + "drilling platform, offshore rig": 540, + "drum, membranophone, tympan": 541, + "drumstick": 542, + "dugong, Dugong dugon": 149, + "dumbbell": 543, + "dung beetle": 305, + "ear, spike, capitulum": 998, + "earthstar": 995, + "echidna, spiny anteater, anteater": 102, + "eel": 390, + "eft": 27, + "eggnog": 969, + "electric fan, blower": 545, + "electric guitar": 546, + "electric locomotive": 547, + "electric ray, crampfish, numbfish, torpedo": 5, + "entertainment center": 548, + "envelope": 549, + "espresso": 967, + "espresso maker": 550, + "face powder": 551, + "feather boa, boa": 552, + "fiddler crab": 120, + "fig": 952, + "file, file cabinet, filing cabinet": 553, + "fire engine, fire truck": 555, + "fire screen, fireguard": 556, + "fireboat": 554, + "flagpole, flagstaff": 557, + "flamingo": 130, + "flat-coated retriever": 205, + "flatworm, platyhelminth": 110, + "flute, transverse flute": 558, + "fly": 308, + "folding chair": 559, + "football helmet": 560, + "forklift": 561, + "fountain": 562, + "fountain pen": 563, + "four-poster": 564, + "fox squirrel, eastern fox squirrel, Sciurus niger": 335, + "freight car": 565, + "frilled lizard, Chlamydosaurus kingi": 43, + "frying pan, frypan, skillet": 567, + "fur coat": 568, + "gar, garfish, garpike, billfish, Lepisosteus osseus": 395, + "garbage truck, dustcart": 569, + "garden spider, Aranea diademata": 74, + "garter snake, grass snake": 57, + "gas pump, gasoline pump, petrol pump, island dispenser": 571, + "gasmask, respirator, gas helmet": 570, + "gazelle": 353, + "geyser": 974, + "giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca": 388, + "giant schnauzer": 197, + "gibbon, Hylobates lar": 368, + "go-kart": 573, + "goblet": 572, + "golden retriever": 207, + "goldfinch, Carduelis carduelis": 11, + "goldfish, Carassius auratus": 1, + "golf ball": 574, + "golfcart, golf cart": 575, + "gondola": 576, + "gong, tam-tam": 577, + "goose": 99, + "gorilla, Gorilla gorilla": 366, + "gown": 578, + "grand piano, grand": 579, + "grasshopper, hopper": 311, + "great grey owl, great gray owl, Strix nebulosa": 24, + "great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias": 2, + "green lizard, Lacerta viridis": 46, + "green mamba": 64, + "green snake, grass snake": 55, + "greenhouse, nursery, glasshouse": 580, + "grey fox, gray fox, Urocyon cinereoargenteus": 280, + "grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus": 147, + "grille, radiator grille": 581, + "grocery store, grocery, food market, market": 582, + "groenendael": 224, + "groom, bridegroom": 982, + "ground beetle, carabid beetle": 302, + "guacamole": 924, + "guenon, guenon monkey": 370, + "guillotine": 583, + "guinea pig, Cavia cobaya": 338, + "gyromitra": 993, + "hair slide": 584, + "hair spray": 585, + "half track": 586, + "hammer": 587, + "hammerhead, hammerhead shark": 4, + "hamper": 588, + "hamster": 333, + "hand blower, blow dryer, blow drier, hair dryer, hair drier": 589, + "hand-held computer, hand-held microcomputer": 590, + "handkerchief, hankie, hanky, hankey": 591, + "hard disc, hard disk, fixed disk": 592, + "hare": 331, + "harmonica, mouth organ, harp, mouth harp": 593, + "harp": 594, + "hartebeest": 351, + "harvester, reaper": 595, + "harvestman, daddy longlegs, Phalangium opilio": 70, + "hatchet": 596, + "hay": 958, + "head cabbage": 936, + "hen": 8, + "hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa": 996, + "hermit crab": 125, + "hip, rose hip, rosehip": 989, + "hippopotamus, hippo, river horse, Hippopotamus amphibius": 344, + "hog, pig, grunter, squealer, Sus scrofa": 341, + "hognose snake, puff adder, sand viper": 54, + "holster": 597, + "home theater, home theatre": 598, + "honeycomb": 599, + "hook, claw": 600, + "hoopskirt, crinoline": 601, + "horizontal bar, high bar": 602, + "hornbill": 93, + "horned viper, cerastes, sand viper, horned asp, Cerastes cornutus": 66, + "horse cart, horse-cart": 603, + "hot pot, hotpot": 926, + "hotdog, hot dog, red hot": 934, + "hourglass": 604, + "house finch, linnet, Carpodacus mexicanus": 12, + "howler monkey, howler": 379, + "hummingbird": 94, + "hyena, hyaena": 276, + "iPod": 605, + "ibex, Capra ibex": 350, + "ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus": 296, + "ice cream, icecream": 928, + "ice lolly, lolly, lollipop, popsicle": 929, + "impala, Aepyceros melampus": 352, + "indigo bunting, indigo finch, indigo bird, Passerina cyanea": 14, + "indri, indris, Indri indri, Indri brevicaudatus": 384, + "iron, smoothing iron": 606, + "isopod": 126, + "jacamar": 95, + "jack-o'-lantern": 607, + "jackfruit, jak, jack": 955, + "jaguar, panther, Panthera onca, Felis onca": 290, + "jay": 17, + "jean, blue jean, denim": 608, + "jeep, landrover": 609, + "jellyfish": 107, + "jersey, T-shirt, tee shirt": 610, + "jigsaw puzzle": 611, + "jinrikisha, ricksha, rickshaw": 612, + "joystick": 613, + "junco, snowbird": 13, + "keeshond": 261, + "kelpie": 227, + "killer whale, killer, orca, grampus, sea wolf, Orcinus orca": 148, + "kimono": 614, + "king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica": 121, + "king penguin, Aptenodytes patagonica": 145, + "king snake, kingsnake": 56, + "kit fox, Vulpes macrotis": 278, + "kite": 21, + "knee pad": 615, + "knot": 616, + "koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus": 105, + "komondor": 228, + "kuvasz": 222, + "lab coat, laboratory coat": 617, + "lacewing, lacewing fly": 318, + "ladle": 618, + "ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle": 301, + "lakeside, lakeshore": 975, + "lampshade, lamp shade": 619, + "langur": 374, + "laptop, laptop computer": 620, + "lawn mower, mower": 621, + "leaf beetle, chrysomelid": 304, + "leafhopper": 317, + "leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea": 34, + "lemon": 951, + "lens cap, lens cover": 622, + "leopard, Panthera pardus": 288, + "lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens": 387, + "letter opener, paper knife, paperknife": 623, + "library": 624, + "lifeboat": 625, + "lighter, light, igniter, ignitor": 626, + "limousine, limo": 627, + "limpkin, Aramus pictus": 135, + "liner, ocean liner": 628, + "lion, king of beasts, Panthera leo": 291, + "lionfish": 396, + "lipstick, lip rouge": 629, + "little blue heron, Egretta caerulea": 131, + "llama": 355, + "loggerhead, loggerhead turtle, Caretta caretta": 33, + "long-horned beetle, longicorn, longicorn beetle": 303, + "lorikeet": 90, + "lotion": 631, + "loudspeaker, speaker, speaker unit, loudspeaker system, speaker system": 632, + "loupe, jeweler's loupe": 633, + "lumbermill, sawmill": 634, + "lycaenid, lycaenid butterfly": 326, + "lynx, catamount": 287, + "macaque": 373, + "macaw": 88, + "magnetic compass": 635, + "magpie": 18, + "mailbag, postbag": 636, + "mailbox, letter box": 637, + "maillot": 638, + "maillot, tank suit": 639, + "malamute, malemute, Alaskan malamute": 249, + "malinois": 225, + "manhole cover": 640, + "mantis, mantid": 315, + "maraca": 641, + "marimba, xylophone": 642, + "marmoset": 377, + "marmot": 336, + "mashed potato": 935, + "mask": 643, + "matchstick": 644, + "maypole": 645, + "maze, labyrinth": 646, + "measuring cup": 647, + "meat loaf, meatloaf": 962, + "medicine chest, medicine cabinet": 648, + "meerkat, mierkat": 299, + "megalith, megalithic structure": 649, + "menu": 922, + "microphone, mike": 650, + "microwave, microwave oven": 651, + "military uniform": 652, + "milk can": 653, + "miniature pinscher": 237, + "miniature poodle": 266, + "miniature schnauzer": 196, + "minibus": 654, + "miniskirt, mini": 655, + "minivan": 656, + "mink": 357, + "missile": 657, + "mitten": 658, + "mixing bowl": 659, + "mobile home, manufactured home": 660, + "modem": 662, + "monarch, monarch butterfly, milkweed butterfly, Danaus plexippus": 323, + "monastery": 663, + "mongoose": 298, + "monitor": 664, + "moped": 665, + "mortar": 666, + "mortarboard": 667, + "mosque": 668, + "mosquito net": 669, + "motor scooter, scooter": 670, + "mountain bike, all-terrain bike, off-roader": 671, + "mountain tent": 672, + "mouse, computer mouse": 673, + "mousetrap": 674, + "moving van": 675, + "mud turtle": 35, + "mushroom": 947, + "muzzle": 676, + "nail": 677, + "neck brace": 678, + "necklace": 679, + "nematode, nematode worm, roundworm": 111, + "night snake, Hypsiglena torquata": 60, + "nipple": 680, + "notebook, notebook computer": 681, + "obelisk": 682, + "oboe, hautboy, hautbois": 683, + "ocarina, sweet potato": 684, + "odometer, hodometer, mileometer, milometer": 685, + "oil filter": 686, + "orange": 950, + "orangutan, orang, orangutang, Pongo pygmaeus": 365, + "organ, pipe organ": 687, + "oscilloscope, scope, cathode-ray oscilloscope, CRO": 688, + "ostrich, Struthio camelus": 9, + "otter": 360, + "otterhound, otter hound": 175, + "overskirt": 689, + "ox": 345, + "oxcart": 690, + "oxygen mask": 691, + "oystercatcher, oyster catcher": 143, + "packet": 692, + "paddle, boat paddle": 693, + "paddlewheel, paddle wheel": 694, + "padlock": 695, + "paintbrush": 696, + "pajama, pyjama, pj's, jammies": 697, + "palace": 698, + "panpipe, pandean pipe, syrinx": 699, + "paper towel": 700, + "papillon": 157, + "parachute, chute": 701, + "parallel bars, bars": 702, + "park bench": 703, + "parking meter": 704, + "partridge": 86, + "passenger car, coach, carriage": 705, + "patas, hussar monkey, Erythrocebus patas": 371, + "patio, terrace": 706, + "pay-phone, pay-station": 707, + "peacock": 84, + "pedestal, plinth, footstall": 708, + "pelican": 144, + "pencil box, pencil case": 709, + "pencil sharpener": 710, + "perfume, essence": 711, + "photocopier": 713, + "pick, plectrum, plectron": 714, + "pickelhaube": 715, + "picket fence, paling": 716, + "pickup, pickup truck": 717, + "pier": 718, + "piggy bank, penny bank": 719, + "pill bottle": 720, + "pillow": 721, + "pineapple, ananas": 953, + "ping-pong ball": 722, + "pinwheel": 723, + "pirate, pirate ship": 724, + "pitcher, ewer": 725, + "pizza, pizza pie": 963, + "plane, carpenter's plane, woodworking plane": 726, + "planetarium": 727, + "plastic bag": 728, + "plate": 923, + "plate rack": 729, + "platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus": 103, + "plow, plough": 730, + "plunger, plumber's helper": 731, + "pole": 733, + "polecat, fitch, foulmart, foumart, Mustela putorius": 358, + "police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria": 734, + "pomegranate": 957, + "poncho": 735, + "pool table, billiard table, snooker table": 736, + "pop bottle, soda bottle": 737, + "porcupine, hedgehog": 334, + "pot, flowerpot": 738, + "potpie": 964, + "potter's wheel": 739, + "power drill": 740, + "prairie chicken, prairie grouse, prairie fowl": 83, + "prayer rug, prayer mat": 741, + "pretzel": 932, + "printer": 742, + "prison, prison house": 743, + "proboscis monkey, Nasalis larvatus": 376, + "projectile, missile": 744, + "projector": 745, + "promontory, headland, head, foreland": 976, + "ptarmigan": 81, + "puck, hockey puck": 746, + "puffer, pufferfish, blowfish, globefish": 397, + "pug, pug-dog": 254, + "punching bag, punch bag, punching ball, punchball": 747, + "purse": 748, + "quail": 85, + "quill, quill pen": 749, + "quilt, comforter, comfort, puff": 750, + "racer, race car, racing car": 751, + "racket, racquet": 752, + "radiator": 753, + "radio telescope, radio reflector": 755, + "radio, wireless": 754, + "rain barrel": 756, + "ram, tup": 348, + "rapeseed": 984, + "recreational vehicle, RV, R.V.": 757, + "red fox, Vulpes vulpes": 277, + "red wine": 966, + "red wolf, maned wolf, Canis rufus, Canis niger": 271, + "red-backed sandpiper, dunlin, Erolia alpina": 140, + "red-breasted merganser, Mergus serrator": 98, + "redbone": 168, + "redshank, Tringa totanus": 141, + "reel": 758, + "reflex camera": 759, + "refrigerator, icebox": 760, + "remote control, remote": 761, + "restaurant, eating house, eating place, eatery": 762, + "revolver, six-gun, six-shooter": 763, + "rhinoceros beetle": 306, + "rifle": 764, + "ringlet, ringlet butterfly": 322, + "ringneck snake, ring-necked snake, ring snake": 53, + "robin, American robin, Turdus migratorius": 15, + "rock beauty, Holocanthus tricolor": 392, + "rock crab, Cancer irroratus": 119, + "rock python, rock snake, Python sebae": 62, + "rocking chair, rocker": 765, + "rotisserie": 766, + "rubber eraser, rubber, pencil eraser": 767, + "ruddy turnstone, Arenaria interpres": 139, + "ruffed grouse, partridge, Bonasa umbellus": 82, + "rugby ball": 768, + "rule, ruler": 769, + "running shoe": 770, + "safe": 771, + "safety pin": 772, + "saltshaker, salt shaker": 773, + "sandal": 774, + "sandbar, sand bar": 977, + "sarong": 775, + "sax, saxophone": 776, + "scabbard": 777, + "scale, weighing machine": 778, + "schipperke": 223, + "school bus": 779, + "schooner": 780, + "scoreboard": 781, + "scorpion": 71, + "screen, CRT screen": 782, + "screw": 783, + "screwdriver": 784, + "scuba diver": 983, + "sea anemone, anemone": 108, + "sea cucumber, holothurian": 329, + "sea lion": 150, + "sea slug, nudibranch": 115, + "sea snake": 65, + "sea urchin": 328, + "seashore, coast, seacoast, sea-coast": 978, + "seat belt, seatbelt": 785, + "sewing machine": 786, + "shield, buckler": 787, + "shoe shop, shoe-shop, shoe store": 788, + "shoji": 789, + "shopping basket": 790, + "shopping cart": 791, + "shovel": 792, + "shower cap": 793, + "shower curtain": 794, + "siamang, Hylobates syndactylus, Symphalangus syndactylus": 369, + "sidewinder, horned rattlesnake, Crotalus cerastes": 68, + "silky terrier, Sydney silky": 201, + "ski": 795, + "ski mask": 796, + "skunk, polecat, wood pussy": 361, + "sleeping bag": 797, + "slide rule, slipstick": 798, + "sliding door": 799, + "slot, one-armed bandit": 800, + "sloth bear, Melursus ursinus, Ursus ursinus": 297, + "slug": 114, + "snail": 113, + "snorkel": 801, + "snow leopard, ounce, Panthera uncia": 289, + "snowmobile": 802, + "snowplow, snowplough": 803, + "soap dispenser": 804, + "soccer ball": 805, + "sock": 806, + "soft-coated wheaten terrier": 202, + "solar dish, solar collector, solar furnace": 807, + "sombrero": 808, + "sorrel": 339, + "soup bowl": 809, + "space bar": 810, + "space heater": 811, + "space shuttle": 812, + "spaghetti squash": 940, + "spatula": 813, + "speedboat": 814, + "spider monkey, Ateles geoffroyi": 381, + "spider web, spider's web": 815, + "spindle": 816, + "spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish": 123, + "spoonbill": 129, + "sports car, sport car": 817, + "spotlight, spot": 818, + "spotted salamander, Ambystoma maculatum": 28, + "squirrel monkey, Saimiri sciureus": 382, + "stage": 819, + "standard poodle": 267, + "standard schnauzer": 198, + "starfish, sea star": 327, + "steam locomotive": 820, + "steel arch bridge": 821, + "steel drum": 822, + "stethoscope": 823, + "stingray": 6, + "stinkhorn, carrion fungus": 994, + "stole": 824, + "stone wall": 825, + "stopwatch, stop watch": 826, + "stove": 827, + "strainer": 828, + "strawberry": 949, + "street sign": 919, + "streetcar, tram, tramcar, trolley, trolley car": 829, + "stretcher": 830, + "studio couch, day bed": 831, + "stupa, tope": 832, + "sturgeon": 394, + "submarine, pigboat, sub, U-boat": 833, + "suit, suit of clothes": 834, + "sulphur butterfly, sulfur butterfly": 325, + "sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita": 89, + "sundial": 835, + "sunglass": 836, + "sunglasses, dark glasses, shades": 837, + "sunscreen, sunblock, sun blocker": 838, + "suspension bridge": 839, + "swab, swob, mop": 840, + "sweatshirt": 841, + "swimming trunks, bathing trunks": 842, + "swing": 843, + "switch, electric switch, electrical switch": 844, + "syringe": 845, + "tabby, tabby cat": 281, + "table lamp": 846, + "tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui": 32, + "tank, army tank, armored combat vehicle, armoured combat vehicle": 847, + "tape player": 848, + "tarantula": 76, + "teapot": 849, + "teddy, teddy bear": 850, + "television, television system": 851, + "tench, Tinca tinca": 0, + "tennis ball": 852, + "terrapin": 36, + "thatch, thatched roof": 853, + "theater curtain, theatre curtain": 854, + "thimble": 855, + "three-toed sloth, ai, Bradypus tridactylus": 364, + "thresher, thrasher, threshing machine": 856, + "throne": 857, + "thunder snake, worm snake, Carphophis amoenus": 52, + "tick": 78, + "tiger beetle": 300, + "tiger cat": 282, + "tiger shark, Galeocerdo cuvieri": 3, + "tiger, Panthera tigris": 292, + "tile roof": 858, + "timber wolf, grey wolf, gray wolf, Canis lupus": 269, + "titi, titi monkey": 380, + "toaster": 859, + "tobacco shop, tobacconist shop, tobacconist": 860, + "toilet seat": 861, + "toilet tissue, toilet paper, bathroom tissue": 999, + "torch": 862, + "totem pole": 863, + "toucan": 96, + "tow truck, tow car, wrecker": 864, + "toy poodle": 265, + "toy terrier": 158, + "toyshop": 865, + "tractor": 866, + "traffic light, traffic signal, stoplight": 920, + "trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi": 867, + "tray": 868, + "tree frog, tree-frog": 31, + "trench coat": 869, + "triceratops": 51, + "tricycle, trike, velocipede": 870, + "trifle": 927, + "trilobite": 69, + "trimaran": 871, + "tripod": 872, + "triumphal arch": 873, + "trolleybus, trolley coach, trackless trolley": 874, + "trombone": 875, + "tub, vat": 876, + "turnstile": 877, + "tusker": 101, + "typewriter keyboard": 878, + "umbrella": 879, + "unicycle, monocycle": 880, + "upright, upright piano": 881, + "vacuum, vacuum cleaner": 882, + "valley, vale": 979, + "vase": 883, + "vault": 884, + "velvet": 885, + "vending machine": 886, + "vestment": 887, + "viaduct": 888, + "vine snake": 59, + "violin, fiddle": 889, + "vizsla, Hungarian pointer": 211, + "volcano": 980, + "volleyball": 890, + "vulture": 23, + "waffle iron": 891, + "walking stick, walkingstick, stick insect": 313, + "wall clock": 892, + "wallaby, brush kangaroo": 104, + "wallet, billfold, notecase, pocketbook": 893, + "wardrobe, closet, press": 894, + "warplane, military plane": 895, + "warthog": 343, + "washbasin, handbasin, washbowl, lavabo, wash-hand basin": 896, + "washer, automatic washer, washing machine": 897, + "water bottle": 898, + "water buffalo, water ox, Asiatic buffalo, Bubalus bubalis": 346, + "water jug": 899, + "water ouzel, dipper": 20, + "water snake": 58, + "water tower": 900, + "weasel": 356, + "web site, website, internet site, site": 916, + "weevil": 307, + "whippet": 172, + "whiptail, whiptail lizard": 41, + "whiskey jug": 901, + "whistle": 902, + "white stork, Ciconia ciconia": 127, + "white wolf, Arctic wolf, Canis lupus tundrarum": 270, + "wig": 903, + "wild boar, boar, Sus scrofa": 342, + "window screen": 904, + "window shade": 905, + "wine bottle": 907, + "wing": 908, + "wire-haired fox terrier": 188, + "wok": 909, + "wolf spider, hunting spider": 77, + "wombat": 106, + "wood rabbit, cottontail, cottontail rabbit": 330, + "wooden spoon": 910, + "wool, woolen, woollen": 911, + "worm fence, snake fence, snake-rail fence, Virginia fence": 912, + "wreck": 913, + "yawl": 914, + "yellow lady's slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum": 986, + "yurt": 915, + "zebra": 340, + "zucchini, courgette": 939 + }, + "layer_norm_eps": 1e-05, + "mlp_ratio": 2.0, + "model_type": "mobilevit", + "neck_hidden_sizes": [ + 4, + 8, + 16, + 24, + 32, + 40, + 160 + ], + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mobilevit", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 2, + "num_channels": 3, + "output_stride": 32, + "patch_size": 2, + "qkv_bias": true, + "semantic_loss_ignore_index": 255 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b66849c636272ba42573115dd9e9121cd9a1f23eee070bb3c29d20d8afc2daf5/48fdbca940072d3e81aa.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b66849c636272ba42573115dd9e9121cd9a1f23eee070bb3c29d20d8afc2daf5/48fdbca940072d3e81aa.json new file mode 100644 index 0000000000000000000000000000000000000000..c570966331285a89ebc56d6fbc7f5a7779d51f68 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b66849c636272ba42573115dd9e9121cd9a1f23eee070bb3c29d20d8afc2daf5/48fdbca940072d3e81aa.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RoFormerModel", + "_task": "token-classification", + "add_cross_attention": false, + "architectures": [ + "RoFormerModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roformer", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roformer", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "rotary_value": false, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 50000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b6d170ebe4048bc6ec52c577b71333e5dbad88439b07c564b5c5726147f3f22a/1be343b49fdcf56bc70f.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b6d170ebe4048bc6ec52c577b71333e5dbad88439b07c564b5c5726147f3f22a/1be343b49fdcf56bc70f.json new file mode 100644 index 0000000000000000000000000000000000000000..c3093ff46fe3650a6135ff0adbe1c7563f0bab56 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b6d170ebe4048bc6ec52c577b71333e5dbad88439b07c564b5c5726147f3f22a/1be343b49fdcf56bc70f.json @@ -0,0 +1,98 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "flaubert/flaubert_small_cased", + "_task": "token-classification", + "amp": 1, + "architectures": [ + "FlaubertWithLMHeadModel" + ], + "asm": false, + "attention_dropout": 0.1, + "bos_index": 0, + "bptt": 512, + "causal": false, + "clip_grad_norm": 5, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 512, + "embed_init_std": 0.02209708691207961, + "encoder_only": true, + "end_n_top": 5, + "eos_index": 1, + "fp16": true, + "gelu_activation": true, + "group_by_size": true, + "id2lang": { + "0": "fr" + }, + "init_std": 0.02, + "is_encoder": true, + "lang2id": { + "fr": 0 + }, + "lang_id": 0, + "langs": [ + "fr" + ], + "layer_norm_eps": 1e-06, + "layerdrop": 0.2, + "lg_sampling_factor": -1, + "lgs": "fr", + "mask_index": 5, + "mask_token_id": 0, + "max_batch_size": 0, + "max_position_embeddings": 512, + "max_vocab": -1, + "mlm_steps": [ + [ + "fr", + null + ] + ], + "model_type": "flaubert", + "n_heads": 8, + "n_langs": 1, + "n_layers": 6, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "flaubert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "pad_index": 2, + "pre_norm": true, + "sample_alpha": 0, + "share_inout_emb": true, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "first", + "summary_use_proj": true, + "tokens_per_batch": -1, + "unk_index": 3, + "use_lang_emb": true, + "vocab_size": 68729, + "word_blank": 0, + "word_dropout": 0, + "word_keep": 0.1, + "word_mask": 0.8, + "word_mask_keep_rand": "0.8,0.1,0.1", + "word_pred": 0.15, + "word_rand": 0.1, + "word_shuffle": 0 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b9f6d30bea4e4cf2d462b8dd9e69d5110baf3d83715a0b4c9cc833aa0687f7a8/d3fc2928804a9a4ebdae.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b9f6d30bea4e4cf2d462b8dd9e69d5110baf3d83715a0b4c9cc833aa0687f7a8/d3fc2928804a9a4ebdae.json new file mode 100644 index 0000000000000000000000000000000000000000..e74865548fbf0094568afe6579587cbf642fd283 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b9f6d30bea4e4cf2d462b8dd9e69d5110baf3d83715a0b4c9cc833aa0687f7a8/d3fc2928804a9a4ebdae.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RobertaModel", + "_task": "feature-extraction", + "architectures": [ + "RobertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1024 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bdb9832cea392343a335006590e8f9deaec7cbfc3b2cbce88d3fbe51940114c2/e212afa9fb839f7db8da.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bdb9832cea392343a335006590e8f9deaec7cbfc3b2cbce88d3fbe51940114c2/e212afa9fb839f7db8da.json new file mode 100644 index 0000000000000000000000000000000000000000..94b4497ceda1be2bc264418b4a9a109ae7aa3fe9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bdb9832cea392343a335006590e8f9deaec7cbfc3b2cbce88d3fbe51940114c2/e212afa9fb839f7db8da.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MobileBertModel", + "_task": "question-answering", + "architectures": [ + "MobileBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_activation": true, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 37, + "intra_bottleneck_size": 128, + "key_query_shared_bottleneck": true, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mobilebert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mobilebert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "normalization_type": "no_norm", + "num_attention_heads": 4, + "num_feedforward_networks": 4, + "num_hidden_layers": 5, + "trigram_input": true, + "true_hidden_size": 128, + "type_vocab_size": 16, + "use_bottleneck": true, + "use_bottleneck_attention": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bee7972b11fa468908b83176873301b4097409742da4833f685549bf051bd9a0/a5533dd8e8a91c9530a1.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bee7972b11fa468908b83176873301b4097409742da4833f685549bf051bd9a0/a5533dd8e8a91c9530a1.json new file mode 100644 index 0000000000000000000000000000000000000000..4c3cea83618b47271daed4d01b6e399f8ecafd7c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bee7972b11fa468908b83176873301b4097409742da4833f685549bf051bd9a0/a5533dd8e8a91c9530a1.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DebertaModel", + "_task": "feature-extraction", + "architectures": [ + "DebertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-07, + "legacy": true, + "max_position_embeddings": 512, + "max_relative_positions": -1, + "model_type": "deberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "deberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "pooler_dropout": 0, + "pooler_hidden_act": "gelu", + "pooler_hidden_size": 32, + "pos_att_type": [ + "none" + ], + "position_biased_input": true, + "relative_attention": false, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 1024 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bert/Jingya/tiny-random-bert-remote-code/8f48534743910791837b.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bert/Jingya/tiny-random-bert-remote-code/8f48534743910791837b.json new file mode 100644 index 0000000000000000000000000000000000000000..996e3be1336452028cafbd0af623fa88f42b89a4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bert/Jingya/tiny-random-bert-remote-code/8f48534743910791837b.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Jingya/tiny-random-bert-remote-code", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bert/fxmarty/tiny-bert-sst2-distilled-subfolder/f326b0b3eb83f8bd7f14.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bert/fxmarty/tiny-bert-sst2-distilled-subfolder/f326b0b3eb83f8bd7f14.json new file mode 100644 index 0000000000000000000000000000000000000000..1a5ef611715e467f429261428e6fec1c16537504 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bert/fxmarty/tiny-bert-sst2-distilled-subfolder/f326b0b3eb83f8bd7f14.json @@ -0,0 +1,56 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "fxmarty/tiny-bert-sst2-distilled-subfolder", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "BertForSequenceClassification" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 128, + "id2label": { + "0": "negative", + "1": "positive" + }, + "initializer_range": 0.02, + "intermediate_size": 512, + "is_decoder": false, + "label2id": { + "negative": "0", + "positive": "1" + }, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "position_embedding_type": "absolute", + "problem_type": "single_label_classification", + "tie_word_embeddings": true, + "type_vocab_size": 2, + "use_cache": true, + "vocab_size": 30522 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bert/hf-internal-testing/tiny-random-BertModel/42fb5b9025ad50931cbf.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bert/hf-internal-testing/tiny-random-BertModel/42fb5b9025ad50931cbf.json new file mode 100644 index 0000000000000000000000000000000000000000..6753aa0c5508eabba457b63588e270702f31c316 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bert/hf-internal-testing/tiny-random-BertModel/42fb5b9025ad50931cbf.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "text-classification", + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": false, + "instance_type": "inf2", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 16, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bert/sentence-transformers/all-MiniLM-L6-v2/949da88be1660765ad17.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bert/sentence-transformers/all-MiniLM-L6-v2/949da88be1660765ad17.json new file mode 100644 index 0000000000000000000000000000000000000000..5ef5547c3223abf86e896fdd9ea71d0c20b7a1df --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bert/sentence-transformers/all-MiniLM-L6-v2/949da88be1660765ad17.json @@ -0,0 +1,49 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "sentence-transformers/all-MiniLM-L6-v2", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "export_model_type": "transformer", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 384, + "initializer_range": 0.02, + "intermediate_size": 1536, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "transformer", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 16, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 12, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 2, + "use_cache": true, + "vocab_size": 30522 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bf3c0823f18995679d9adc80e374ab26d710bee4c7e6c1156c2e4c0688ca06e9/f78454cba5a7dc3be4ca.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bf3c0823f18995679d9adc80e374ab26d710bee4c7e6c1156c2e4c0688ca06e9/f78454cba5a7dc3be4ca.json new file mode 100644 index 0000000000000000000000000000000000000000..72cf2160b75392906048c290fafbf5bf4f5c2bd1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/bf3c0823f18995679d9adc80e374ab26d710bee4c7e6c1156c2e4c0688ca06e9/f78454cba5a7dc3be4ca.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RoFormerModel", + "_task": "question-answering", + "architectures": [ + "RoFormerModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roformer", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roformer", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "rotary_value": false, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 50000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c0fa7396bca6a1e0a007e388623491303a60d115c2a501cd11d08e8b994cb573/7956f2bd4f8e671f6e6a.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c0fa7396bca6a1e0a007e388623491303a60d115c2a501cd11d08e8b994cb573/7956f2bd4f8e671f6e6a.json new file mode 100644 index 0000000000000000000000000000000000000000..ce9d53b4297b12eb8eab8d57fa6a7cffb87aa9dc --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c0fa7396bca6a1e0a007e388623491303a60d115c2a501cd11d08e8b994cb573/7956f2bd4f8e671f6e6a.json @@ -0,0 +1,42 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MPNetModel", + "_task": "feature-extraction", + "architectures": [ + "MPNetModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 64, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mpnet", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mpnet", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "relative_attention_num_buckets": 32, + "tie_word_embeddings": true, + "vocab_size": 1125 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c2f0c45432702b5ffed42455121c585aa75fcd154ec1ad6cd7940b022b31d59d/3f2915b0d9944f88f3d0.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c2f0c45432702b5ffed42455121c585aa75fcd154ec1ad6cd7940b022b31d59d/3f2915b0d9944f88f3d0.json new file mode 100644 index 0000000000000000000000000000000000000000..f99f630a5e9290e5fd797aecfa70df89c19196e1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c2f0c45432702b5ffed42455121c585aa75fcd154ec1ad6cd7940b022b31d59d/3f2915b0d9944f88f3d0.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "feature-extraction", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 16, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c2f0c45432702b5ffed42455121c585aa75fcd154ec1ad6cd7940b022b31d59d/45a22c33e6d99d6172fa.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c2f0c45432702b5ffed42455121c585aa75fcd154ec1ad6cd7940b022b31d59d/45a22c33e6d99d6172fa.json new file mode 100644 index 0000000000000000000000000000000000000000..b704fd06349ff776f45bcb87209da37e45f75f5b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c2f0c45432702b5ffed42455121c585aa75fcd154ec1ad6cd7940b022b31d59d/45a22c33e6d99d6172fa.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "feature-extraction", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c2f0c45432702b5ffed42455121c585aa75fcd154ec1ad6cd7940b022b31d59d/64478ebb487b37ac6eaf.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c2f0c45432702b5ffed42455121c585aa75fcd154ec1ad6cd7940b022b31d59d/64478ebb487b37ac6eaf.json new file mode 100644 index 0000000000000000000000000000000000000000..c4c9917be9de4021c4df7eccb8c0f5df364c1ec8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c2f0c45432702b5ffed42455121c585aa75fcd154ec1ad6cd7940b022b31d59d/64478ebb487b37ac6eaf.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "feature-extraction", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c2f0c45432702b5ffed42455121c585aa75fcd154ec1ad6cd7940b022b31d59d/64fcfee6a6ac5b254aae.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c2f0c45432702b5ffed42455121c585aa75fcd154ec1ad6cd7940b022b31d59d/64fcfee6a6ac5b254aae.json new file mode 100644 index 0000000000000000000000000000000000000000..d75889db6bff42d9eed6c8897ced70cf0063c0ed --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c2f0c45432702b5ffed42455121c585aa75fcd154ec1ad6cd7940b022b31d59d/64fcfee6a6ac5b254aae.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "feature-extraction", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c3eab0e29dd0b09f8e914360f2b831720925e17c385a96a080f5018345fa3061/81c89c519f7c5ec84f04.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c3eab0e29dd0b09f8e914360f2b831720925e17c385a96a080f5018345fa3061/81c89c519f7c5ec84f04.json new file mode 100644 index 0000000000000000000000000000000000000000..9015887e4556f2f5f8aadf491182597765bb1451 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c3eab0e29dd0b09f8e914360f2b831720925e17c385a96a080f5018345fa3061/81c89c519f7c5ec84f04.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-XLMModel", + "_task": "fill-mask", + "architectures": [ + "XLMModel" + ], + "asm": false, + "attention_dropout": 0.1, + "bos_index": 0, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "eos_index": 1, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "mask_index": 5, + "mask_token_id": 5, + "max_position_embeddings": 512, + "model_type": "xlm", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "xlm", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "pad_index": 2, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": true, + "vocab_size": 30145 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c7530ee8ee3a31cffb361e3acaf1be152b7b96d883981a1e7c82a3540bd5113a/f326b0b3eb83f8bd7f14.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c7530ee8ee3a31cffb361e3acaf1be152b7b96d883981a1e7c82a3540bd5113a/f326b0b3eb83f8bd7f14.json new file mode 100644 index 0000000000000000000000000000000000000000..1a5ef611715e467f429261428e6fec1c16537504 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/c7530ee8ee3a31cffb361e3acaf1be152b7b96d883981a1e7c82a3540bd5113a/f326b0b3eb83f8bd7f14.json @@ -0,0 +1,56 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "fxmarty/tiny-bert-sst2-distilled-subfolder", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "BertForSequenceClassification" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 128, + "id2label": { + "0": "negative", + "1": "positive" + }, + "initializer_range": 0.02, + "intermediate_size": 512, + "is_decoder": false, + "label2id": { + "negative": "0", + "positive": "1" + }, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "position_embedding_type": "absolute", + "problem_type": "single_label_classification", + "tie_word_embeddings": true, + "type_vocab_size": 2, + "use_cache": true, + "vocab_size": 30522 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/camembert/hf-internal-testing/tiny-random-camembert/3bceb7d639ac50f4e447.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/camembert/hf-internal-testing/tiny-random-camembert/3bceb7d639ac50f4e447.json new file mode 100644 index 0000000000000000000000000000000000000000..da8341207ec39896026ff6a59833a7f5e893b26c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/camembert/hf-internal-testing/tiny-random-camembert/3bceb7d639ac50f4e447.json @@ -0,0 +1,45 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-camembert", + "_task": "question-answering", + "architectures": [ + "CamembertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "camembert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "camembert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/clip/sentence-transformers/clip-ViT-B-32/1b803b56ab36d04761b2.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/clip/sentence-transformers/clip-ViT-B-32/1b803b56ab36d04761b2.json new file mode 100644 index 0000000000000000000000000000000000000000..bde0a677728a0f5514970996d57646766c851abf --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/clip/sentence-transformers/clip-ViT-B-32/1b803b56ab36d04761b2.json @@ -0,0 +1,105 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "sentence-transformers/clip-ViT-B-32", + "_task": "feature-extraction", + "architectures": [ + "CLIPModel" + ], + "dtype": "float32", + "export_model_type": "clip", + "initializer_factor": 1.0, + "logit_scale_init_value": 2.6592, + "model_type": "clip", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "clip", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_height": 224, + "static_image_batch_size": 1, + "static_num_channels": 3, + "static_sequence_length": 16, + "static_text_batch_size": 3, + "static_width": 224, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "text_config": { + "add_cross_attention": false, + "attention_dropout": 0.0, + "bos_token_id": 0, + "decoder_start_token_id": null, + "dropout": 0.0, + "dtype": "float32", + "eos_token_id": 2, + "finetuning_task": null, + "gradient_checkpointing": false, + "hidden_act": "quick_gelu", + "hidden_size": 512, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 2048, + "is_decoder": false, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "num_attention_heads": 8, + "num_hidden_layers": 12, + "pad_token_id": 1, + "prefix": null, + "projection_dim": 512, + "pruned_heads": {}, + "sep_token_id": null, + "task_specific_params": null, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "torchscript": false, + "use_bfloat16": false, + "vocab_size": 49408 + }, + "vision_config": { + "add_cross_attention": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "decoder_start_token_id": null, + "dropout": 0.0, + "dtype": "float32", + "eos_token_id": null, + "finetuning_task": null, + "gradient_checkpointing": false, + "hidden_act": "quick_gelu", + "hidden_size": 768, + "image_size": 224, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 3072, + "is_decoder": false, + "layer_norm_eps": 1e-05, + "model_type": "clip_vision_model", + "num_attention_heads": 12, + "num_channels": 3, + "num_hidden_layers": 12, + "pad_token_id": null, + "patch_size": 32, + "prefix": null, + "projection_dim": 512, + "pruned_heads": {}, + "sep_token_id": null, + "task_specific_params": null, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "torchscript": false, + "use_bfloat16": false + } +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/convbert/hf-internal-testing/tiny-random-ConvBertModel/2d3e547ebbc6fff4f957.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/convbert/hf-internal-testing/tiny-random-ConvBertModel/2d3e547ebbc6fff4f957.json new file mode 100644 index 0000000000000000000000000000000000000000..40e37c48f4d1ed26aa0c798162ba173f20509936 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/convbert/hf-internal-testing/tiny-random-ConvBertModel/2d3e547ebbc6fff4f957.json @@ -0,0 +1,46 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ConvBertModel", + "_task": "text-classification", + "architectures": [ + "ConvBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "conv_kernel_size": 9, + "dtype": "float32", + "embedding_size": 768, + "head_ratio": 2, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "convbert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "convbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_groups": 1, + "num_hidden_layers": 5, + "type_vocab_size": 16, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/d2fa6994b3475fbfa2072e25730adeba3bc4a876af879e4d9f004a7f679230df/ce62f35153447d32b33a.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/d2fa6994b3475fbfa2072e25730adeba3bc4a876af879e4d9f004a7f679230df/ce62f35153447d32b33a.json new file mode 100644 index 0000000000000000000000000000000000000000..523b9e67062d3e0774827f9cb304e2f72d2bc971 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/d2fa6994b3475fbfa2072e25730adeba3bc4a876af879e4d9f004a7f679230df/ce62f35153447d32b33a.json @@ -0,0 +1,98 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "flaubert/flaubert_small_cased", + "_task": "fill-mask", + "amp": 1, + "architectures": [ + "FlaubertWithLMHeadModel" + ], + "asm": false, + "attention_dropout": 0.1, + "bos_index": 0, + "bptt": 512, + "causal": false, + "clip_grad_norm": 5, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 512, + "embed_init_std": 0.02209708691207961, + "encoder_only": true, + "end_n_top": 5, + "eos_index": 1, + "fp16": true, + "gelu_activation": true, + "group_by_size": true, + "id2lang": { + "0": "fr" + }, + "init_std": 0.02, + "is_encoder": true, + "lang2id": { + "fr": 0 + }, + "lang_id": 0, + "langs": [ + "fr" + ], + "layer_norm_eps": 1e-06, + "layerdrop": 0.2, + "lg_sampling_factor": -1, + "lgs": "fr", + "mask_index": 5, + "mask_token_id": 0, + "max_batch_size": 0, + "max_position_embeddings": 512, + "max_vocab": -1, + "mlm_steps": [ + [ + "fr", + null + ] + ], + "model_type": "flaubert", + "n_heads": 8, + "n_langs": 1, + "n_layers": 6, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "flaubert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "pad_index": 2, + "pre_norm": true, + "sample_alpha": 0, + "share_inout_emb": true, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "first", + "summary_use_proj": true, + "tokens_per_batch": -1, + "unk_index": 3, + "use_lang_emb": true, + "vocab_size": 68729, + "word_blank": 0, + "word_dropout": 0, + "word_keep": 0.1, + "word_mask": 0.8, + "word_mask_keep_rand": "0.8,0.1,0.1", + "word_pred": 0.15, + "word_rand": 0.1, + "word_shuffle": 0 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/d5c3655324eb63aaf1213f9327347ee2411ff4672ec2bee9db2a5861b7fbbaf6/1b803b56ab36d04761b2.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/d5c3655324eb63aaf1213f9327347ee2411ff4672ec2bee9db2a5861b7fbbaf6/1b803b56ab36d04761b2.json new file mode 100644 index 0000000000000000000000000000000000000000..bde0a677728a0f5514970996d57646766c851abf --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/d5c3655324eb63aaf1213f9327347ee2411ff4672ec2bee9db2a5861b7fbbaf6/1b803b56ab36d04761b2.json @@ -0,0 +1,105 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "sentence-transformers/clip-ViT-B-32", + "_task": "feature-extraction", + "architectures": [ + "CLIPModel" + ], + "dtype": "float32", + "export_model_type": "clip", + "initializer_factor": 1.0, + "logit_scale_init_value": 2.6592, + "model_type": "clip", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "clip", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_height": 224, + "static_image_batch_size": 1, + "static_num_channels": 3, + "static_sequence_length": 16, + "static_text_batch_size": 3, + "static_width": 224, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "text_config": { + "add_cross_attention": false, + "attention_dropout": 0.0, + "bos_token_id": 0, + "decoder_start_token_id": null, + "dropout": 0.0, + "dtype": "float32", + "eos_token_id": 2, + "finetuning_task": null, + "gradient_checkpointing": false, + "hidden_act": "quick_gelu", + "hidden_size": 512, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 2048, + "is_decoder": false, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "num_attention_heads": 8, + "num_hidden_layers": 12, + "pad_token_id": 1, + "prefix": null, + "projection_dim": 512, + "pruned_heads": {}, + "sep_token_id": null, + "task_specific_params": null, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "torchscript": false, + "use_bfloat16": false, + "vocab_size": 49408 + }, + "vision_config": { + "add_cross_attention": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "decoder_start_token_id": null, + "dropout": 0.0, + "dtype": "float32", + "eos_token_id": null, + "finetuning_task": null, + "gradient_checkpointing": false, + "hidden_act": "quick_gelu", + "hidden_size": 768, + "image_size": 224, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 3072, + "is_decoder": false, + "layer_norm_eps": 1e-05, + "model_type": "clip_vision_model", + "num_attention_heads": 12, + "num_channels": 3, + "num_hidden_layers": 12, + "pad_token_id": null, + "patch_size": 32, + "prefix": null, + "projection_dim": 512, + "pruned_heads": {}, + "sep_token_id": null, + "task_specific_params": null, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "torchscript": false, + "use_bfloat16": false + } +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/d984f4dd4ace7b84ec698f873a04d2bc0f0ae2a185d4caa482dc357ea3af3abd/d7839daf08b64445afdc.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/d984f4dd4ace7b84ec698f873a04d2bc0f0ae2a185d4caa482dc357ea3af3abd/d7839daf08b64445afdc.json new file mode 100644 index 0000000000000000000000000000000000000000..e9b9d2e35c424d398ac1ff2d173c602341d89846 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/d984f4dd4ace7b84ec698f873a04d2bc0f0ae2a185d4caa482dc357ea3af3abd/d7839daf08b64445afdc.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RoFormerModel", + "_task": "question-answering", + "add_cross_attention": false, + "architectures": [ + "RoFormerModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roformer", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roformer", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "rotary_value": false, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 50000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/d9e52daaee42d3947f88de4331c41adfb7d1600928a2b18768f37f4046948a5e/66def36ede3b178de1d2.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/d9e52daaee42d3947f88de4331c41adfb7d1600928a2b18768f37f4046948a5e/66def36ede3b178de1d2.json new file mode 100644 index 0000000000000000000000000000000000000000..2718e80cf79cc97d3c2f6aa1bd612ac1767be832 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/d9e52daaee42d3947f88de4331c41adfb7d1600928a2b18768f37f4046948a5e/66def36ede3b178de1d2.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DistilBertModel", + "_task": "question-answering", + "activation": "gelu", + "architectures": [ + "DistilBertModel" + ], + "attention_dropout": 0.1, + "dim": 32, + "dropout": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dim": 37, + "initializer_range": 0.02, + "max_position_embeddings": 512, + "model_type": "distilbert", + "n_heads": 4, + "n_layers": 5, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "distilbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "qa_dropout": 0.1, + "seq_classif_dropout": 0.2, + "sinusoidal_pos_embds": false, + "tie_word_embeddings": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/dae23f696ea8718024485f8c5b1b7cfd5e5e0fd429be6635bc5c0194b6fbab5c/229bb5e4e86fe9ff670e.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/dae23f696ea8718024485f8c5b1b7cfd5e5e0fd429be6635bc5c0194b6fbab5c/229bb5e4e86fe9ff670e.json new file mode 100644 index 0000000000000000000000000000000000000000..2d398f0975628cd2ee123c61f0d8518b5b36a1c8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/dae23f696ea8718024485f8c5b1b7cfd5e5e0fd429be6635bc5c0194b6fbab5c/229bb5e4e86fe9ff670e.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "text-classification", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/dae23f696ea8718024485f8c5b1b7cfd5e5e0fd429be6635bc5c0194b6fbab5c/797c9729deb0ee745b37.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/dae23f696ea8718024485f8c5b1b7cfd5e5e0fd429be6635bc5c0194b6fbab5c/797c9729deb0ee745b37.json new file mode 100644 index 0000000000000000000000000000000000000000..ea976b162438429c506b58804100dfa8b0bdc8f2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/dae23f696ea8718024485f8c5b1b7cfd5e5e0fd429be6635bc5c0194b6fbab5c/797c9729deb0ee745b37.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "text-classification", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/dae23f696ea8718024485f8c5b1b7cfd5e5e0fd429be6635bc5c0194b6fbab5c/c5e5e6fb46e1ac52067e.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/dae23f696ea8718024485f8c5b1b7cfd5e5e0fd429be6635bc5c0194b6fbab5c/c5e5e6fb46e1ac52067e.json new file mode 100644 index 0000000000000000000000000000000000000000..30702c6e870c5ac2ef5c47e27ba3e01bc636aa46 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/dae23f696ea8718024485f8c5b1b7cfd5e5e0fd429be6635bc5c0194b6fbab5c/c5e5e6fb46e1ac52067e.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "text-classification", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/db45d5446b33efb86c1a8be52af40c82c6aaac40779efaa8274b01fcf6fe5d50/8437fba14c98e04be72c.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/db45d5446b33efb86c1a8be52af40c82c6aaac40779efaa8274b01fcf6fe5d50/8437fba14c98e04be72c.json new file mode 100644 index 0000000000000000000000000000000000000000..09b3d28e4ca958e3f18f1b4b42dc92a8bd56c3fa --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/db45d5446b33efb86c1a8be52af40c82c6aaac40779efaa8274b01fcf6fe5d50/8437fba14c98e04be72c.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "question-answering", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/dbe51f40e81d24e4167db6e562a43ef09bf6e6e3699d4172e26aa7c1888d9c7b/6b2b1bc1dccccceaf91c.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/dbe51f40e81d24e4167db6e562a43ef09bf6e6e3699d4172e26aa7c1888d9c7b/6b2b1bc1dccccceaf91c.json new file mode 100644 index 0000000000000000000000000000000000000000..16411fde8e3e4fbcf3b46379c43c798f19b881cd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/dbe51f40e81d24e4167db6e562a43ef09bf6e6e3699d4172e26aa7c1888d9c7b/6b2b1bc1dccccceaf91c.json @@ -0,0 +1,98 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "flaubert/flaubert_small_cased", + "_task": "question-answering", + "amp": 1, + "architectures": [ + "FlaubertWithLMHeadModel" + ], + "asm": false, + "attention_dropout": 0.1, + "bos_index": 0, + "bptt": 512, + "causal": false, + "clip_grad_norm": 5, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 512, + "embed_init_std": 0.02209708691207961, + "encoder_only": true, + "end_n_top": 5, + "eos_index": 1, + "fp16": true, + "gelu_activation": true, + "group_by_size": true, + "id2lang": { + "0": "fr" + }, + "init_std": 0.02, + "is_encoder": true, + "lang2id": { + "fr": 0 + }, + "lang_id": 0, + "langs": [ + "fr" + ], + "layer_norm_eps": 1e-06, + "layerdrop": 0.2, + "lg_sampling_factor": -1, + "lgs": "fr", + "mask_index": 5, + "mask_token_id": 0, + "max_batch_size": 0, + "max_position_embeddings": 512, + "max_vocab": -1, + "mlm_steps": [ + [ + "fr", + null + ] + ], + "model_type": "flaubert", + "n_heads": 8, + "n_langs": 1, + "n_layers": 6, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "flaubert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "pad_index": 2, + "pre_norm": true, + "sample_alpha": 0, + "share_inout_emb": true, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "first", + "summary_use_proj": true, + "tokens_per_batch": -1, + "unk_index": 3, + "use_lang_emb": true, + "vocab_size": 68729, + "word_blank": 0, + "word_dropout": 0, + "word_keep": 0.1, + "word_mask": 0.8, + "word_mask_keep_rand": "0.8,0.1,0.1", + "word_pred": 0.15, + "word_rand": 0.1, + "word_shuffle": 0 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/dcc942fe869cfca64c08d649c573acbb1257b14c174db49e8340f39034c7eb44/e65562ca1ac02dd41d5c.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/dcc942fe869cfca64c08d649c573acbb1257b14c174db49e8340f39034c7eb44/e65562ca1ac02dd41d5c.json new file mode 100644 index 0000000000000000000000000000000000000000..d435389b76856f4d9a1f51c6cbcaaa31a82bb0ca --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/dcc942fe869cfca64c08d649c573acbb1257b14c174db49e8340f39034c7eb44/e65562ca1ac02dd41d5c.json @@ -0,0 +1,68 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "_task": "text-generation", + "architectures": [ + "Qwen3MoeForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "decoder_sparse_step": 2, + "dtype": "float32", + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 128, + "max_position_embeddings": 40960, + "max_window_layers": 1, + "mlp_only_layers": [], + "model_type": "qwen3_moe", + "moe_intermediate_size": 128, + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "checkpoint_revision": "e0230be2839556b44b7400a233c73c74b4abb7af", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "norm_topk_prob": true, + "num_attention_heads": 2, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "router_aux_loss_coef": 0.001, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ddd395f808b2aeb32e3e830d913872aab3ca18e3fae854b4bf8c7eb09711de59/32895fdbbbfb897551f5.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ddd395f808b2aeb32e3e830d913872aab3ca18e3fae854b4bf8c7eb09711de59/32895fdbbbfb897551f5.json new file mode 100644 index 0000000000000000000000000000000000000000..524b8e49ccc7becdfe7243352711b4a555069a52 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ddd395f808b2aeb32e3e830d913872aab3ca18e3fae854b4bf8c7eb09711de59/32895fdbbbfb897551f5.json @@ -0,0 +1,41 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MPNetModel", + "_task": "question-answering", + "architectures": [ + "MPNetModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 64, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mpnet", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mpnet", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "relative_attention_num_buckets": 32, + "vocab_size": 1125 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/deberta-v2/hf-internal-testing/tiny-random-DebertaV2Model/0fca3e04298ddbbf44ec.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/deberta-v2/hf-internal-testing/tiny-random-DebertaV2Model/0fca3e04298ddbbf44ec.json new file mode 100644 index 0000000000000000000000000000000000000000..d3237331de63ff062bb3fba62159c699edbe9257 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/deberta-v2/hf-internal-testing/tiny-random-DebertaV2Model/0fca3e04298ddbbf44ec.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DebertaV2Model", + "_task": "fill-mask", + "architectures": [ + "DebertaV2Model" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-07, + "legacy": true, + "max_position_embeddings": 512, + "max_relative_positions": -1, + "model_type": "deberta-v2", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "deberta-v2", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "pooler_dropout": 0, + "pooler_hidden_act": "gelu", + "pooler_hidden_size": 32, + "pos_att_type": [ + "none" + ], + "position_biased_input": true, + "relative_attention": false, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 128001 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/deberta/hf-internal-testing/tiny-random-DebertaModel/04b5c83958ebb7367afa.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/deberta/hf-internal-testing/tiny-random-DebertaModel/04b5c83958ebb7367afa.json new file mode 100644 index 0000000000000000000000000000000000000000..815f2be0217c222507e9ae76f7bebc3245747772 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/deberta/hf-internal-testing/tiny-random-DebertaModel/04b5c83958ebb7367afa.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DebertaModel", + "_task": "fill-mask", + "architectures": [ + "DebertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-07, + "legacy": true, + "max_position_embeddings": 512, + "max_relative_positions": -1, + "model_type": "deberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "deberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "pooler_dropout": 0, + "pooler_hidden_act": "gelu", + "pooler_hidden_size": 32, + "pos_att_type": [ + "none" + ], + "position_biased_input": true, + "relative_attention": false, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 1024 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/df82a53cca9af2b0e487ad21906fffa5e7398af8463fdf7f6733428b82af7440/7f9542bc9174cf1efffe.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/df82a53cca9af2b0e487ad21906fffa5e7398af8463fdf7f6733428b82af7440/7f9542bc9174cf1efffe.json new file mode 100644 index 0000000000000000000000000000000000000000..4dc4ca907b59ed5ab29fb34972e3c43275066156 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/df82a53cca9af2b0e487ad21906fffa5e7398af8463fdf7f6733428b82af7440/7f9542bc9174cf1efffe.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-XLMModel", + "_task": "feature-extraction", + "architectures": [ + "XLMModel" + ], + "asm": false, + "attention_dropout": 0.1, + "bos_index": 0, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "eos_index": 1, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "mask_index": 5, + "mask_token_id": 5, + "max_position_embeddings": 512, + "model_type": "xlm", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "xlm", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "pad_index": 2, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": true, + "vocab_size": 30145 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/distilbert/hf-internal-testing/tiny-random-DistilBertModel/2b5ba8600a7737814044.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/distilbert/hf-internal-testing/tiny-random-DistilBertModel/2b5ba8600a7737814044.json new file mode 100644 index 0000000000000000000000000000000000000000..88c5c4294b1c5545da6ad87e14ca781e309f0d7d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/distilbert/hf-internal-testing/tiny-random-DistilBertModel/2b5ba8600a7737814044.json @@ -0,0 +1,43 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DistilBertModel", + "_task": "token-classification", + "activation": "gelu", + "architectures": [ + "DistilBertModel" + ], + "attention_dropout": 0.1, + "dim": 32, + "dropout": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dim": 37, + "initializer_range": 0.02, + "max_position_embeddings": 512, + "model_type": "distilbert", + "n_heads": 4, + "n_layers": 5, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "distilbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "qa_dropout": 0.1, + "seq_classif_dropout": 0.2, + "sinusoidal_pos_embds": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e0344946bbe2036eeb1f10d6c61a78a79a3abc736b84e1ce88f9ee10d734301a/90f7072bebc40ea0b290.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e0344946bbe2036eeb1f10d6c61a78a79a3abc736b84e1ce88f9ee10d734301a/90f7072bebc40ea0b290.json new file mode 100644 index 0000000000000000000000000000000000000000..f901b94561f460aac0503289a527464e3e534a50 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e0344946bbe2036eeb1f10d6c61a78a79a3abc736b84e1ce88f9ee10d734301a/90f7072bebc40ea0b290.json @@ -0,0 +1,98 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "flaubert/flaubert_small_cased", + "_task": "feature-extraction", + "amp": 1, + "architectures": [ + "FlaubertWithLMHeadModel" + ], + "asm": false, + "attention_dropout": 0.1, + "bos_index": 0, + "bptt": 512, + "causal": false, + "clip_grad_norm": 5, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 512, + "embed_init_std": 0.02209708691207961, + "encoder_only": true, + "end_n_top": 5, + "eos_index": 1, + "fp16": true, + "gelu_activation": true, + "group_by_size": true, + "id2lang": { + "0": "fr" + }, + "init_std": 0.02, + "is_encoder": true, + "lang2id": { + "fr": 0 + }, + "lang_id": 0, + "langs": [ + "fr" + ], + "layer_norm_eps": 1e-06, + "layerdrop": 0.2, + "lg_sampling_factor": -1, + "lgs": "fr", + "mask_index": 5, + "mask_token_id": 0, + "max_batch_size": 0, + "max_position_embeddings": 512, + "max_vocab": -1, + "mlm_steps": [ + [ + "fr", + null + ] + ], + "model_type": "flaubert", + "n_heads": 8, + "n_langs": 1, + "n_layers": 6, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "flaubert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "pad_index": 2, + "pre_norm": true, + "sample_alpha": 0, + "share_inout_emb": true, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "first", + "summary_use_proj": true, + "tokens_per_batch": -1, + "unk_index": 3, + "use_lang_emb": true, + "vocab_size": 68729, + "word_blank": 0, + "word_dropout": 0, + "word_keep": 0.1, + "word_mask": 0.8, + "word_mask_keep_rand": "0.8,0.1,0.1", + "word_pred": 0.15, + "word_rand": 0.1, + "word_shuffle": 0 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e35ac0040a27ed049a25c5b6c99a822ee8157a534e3068cfe194d84c5b844833/fa0c3c4b4d230ee3d726.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e35ac0040a27ed049a25c5b6c99a822ee8157a534e3068cfe194d84c5b844833/fa0c3c4b4d230ee3d726.json new file mode 100644 index 0000000000000000000000000000000000000000..7afd2edc88accb964d354d8bf81deb9e676bfb27 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e35ac0040a27ed049a25c5b6c99a822ee8157a534e3068cfe194d84c5b844833/fa0c3c4b4d230ee3d726.json @@ -0,0 +1,138 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolLM3-3B", + "_task": "text-generation", + "architectures": [ + "SmolLM3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 65536, + "max_window_layers": 28, + "mlp_bias": false, + "model_type": "smollm3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolLM3-3B", + "checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layer_interval": 4, + "no_rope_layers": [ + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 4, + "pretraining_tp": 2, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 5000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e55b0039994545b6b1b4dc530dd7e5cb9b742224600b98ba6d5b608799c8b6ba/7e559f18a9703d83ab85.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e55b0039994545b6b1b4dc530dd7e5cb9b742224600b98ba6d5b608799c8b6ba/7e559f18a9703d83ab85.json new file mode 100644 index 0000000000000000000000000000000000000000..6b7b156f70ce0ebf0523d26de559135efdcc5f41 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e55b0039994545b6b1b4dc530dd7e5cb9b742224600b98ba6d5b608799c8b6ba/7e559f18a9703d83ab85.json @@ -0,0 +1,49 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ConvBertModel", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "ConvBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "conv_kernel_size": 9, + "dtype": "float32", + "embedding_size": 768, + "head_ratio": 2, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "convbert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "convbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_groups": 1, + "num_hidden_layers": 5, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e55b0039994545b6b1b4dc530dd7e5cb9b742224600b98ba6d5b608799c8b6ba/d812f434d2f312de98b1.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e55b0039994545b6b1b4dc530dd7e5cb9b742224600b98ba6d5b608799c8b6ba/d812f434d2f312de98b1.json new file mode 100644 index 0000000000000000000000000000000000000000..d7165f4faf55537bbc1ec2cc1f396b34d4d9aee2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e55b0039994545b6b1b4dc530dd7e5cb9b742224600b98ba6d5b608799c8b6ba/d812f434d2f312de98b1.json @@ -0,0 +1,49 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ConvBertModel", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "ConvBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "conv_kernel_size": 9, + "dtype": "float32", + "embedding_size": 768, + "head_ratio": 2, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "convbert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "convbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_groups": 1, + "num_hidden_layers": 5, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e6bab417a36fdc1320b006c201980a1870823d25c6dce396b0210b46f7c37cf1/527ce4bfddfe5f112dc7.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e6bab417a36fdc1320b006c201980a1870823d25c6dce396b0210b46f7c37cf1/527ce4bfddfe5f112dc7.json new file mode 100644 index 0000000000000000000000000000000000000000..ec6f727a313aa2a1fb444cd99fafcdbce2883bbd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e6bab417a36fdc1320b006c201980a1870823d25c6dce396b0210b46f7c37cf1/527ce4bfddfe5f112dc7.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-flaubert", + "_task": "question-answering", + "architectures": [ + "FlaubertModel" + ], + "asm": false, + "attention_dropout": 0.1, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "layerdrop": 0.0, + "mask_index": 5, + "mask_token_id": 0, + "max_position_embeddings": 512, + "model_type": "flaubert", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "flaubert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "pre_norm": false, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "tie_word_embeddings": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": null, + "vocab_size": 68729 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e84dfbfa3376cfc92e75f43973a9c9495d4168529e96431650e9c4afe4a6af2d/9b4e78cba760f7dcf55a.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e84dfbfa3376cfc92e75f43973a9c9495d4168529e96431650e9c4afe4a6af2d/9b4e78cba760f7dcf55a.json new file mode 100644 index 0000000000000000000000000000000000000000..1b608ba2e8be53cff40eb05190d40470b00d9f47 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e84dfbfa3376cfc92e75f43973a9c9495d4168529e96431650e9c4afe4a6af2d/9b4e78cba760f7dcf55a.json @@ -0,0 +1,45 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-camembert", + "_task": "fill-mask", + "architectures": [ + "CamembertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "camembert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "camembert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e9dbfc8a1a14a89c4fb93310f10ccf40311c0b3afbc38893b0395c39844ae29c/9f73b985fae6a7303102.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e9dbfc8a1a14a89c4fb93310f10ccf40311c0b3afbc38893b0395c39844ae29c/9f73b985fae6a7303102.json new file mode 100644 index 0000000000000000000000000000000000000000..c0dfb308421a8467b203ff773709152088302d1c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e9dbfc8a1a14a89c4fb93310f10ccf40311c0b3afbc38893b0395c39844ae29c/9f73b985fae6a7303102.json @@ -0,0 +1,61 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-XLMModel", + "_task": "question-answering", + "architectures": [ + "XLMModel" + ], + "asm": false, + "attention_dropout": 0.1, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "mask_index": 5, + "mask_token_id": 5, + "max_position_embeddings": 512, + "model_type": "xlm", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "xlm", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "tie_word_embeddings": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": true, + "vocab_size": 30145 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ebb9aeeb553a84a750259753a25170c4dc414f9a2c22e8f8aff11c288bd0b100/2941647f732343df72b8.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ebb9aeeb553a84a750259753a25170c4dc414f9a2c22e8f8aff11c288bd0b100/2941647f732343df72b8.json new file mode 100644 index 0000000000000000000000000000000000000000..cfdfad4dbbca44d077959095d27b414cb1eff52f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ebb9aeeb553a84a750259753a25170c4dc414f9a2c22e8f8aff11c288bd0b100/2941647f732343df72b8.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DebertaV2Model", + "_task": "question-answering", + "architectures": [ + "DebertaV2Model" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-07, + "legacy": true, + "max_position_embeddings": 512, + "max_relative_positions": -1, + "model_type": "deberta-v2", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "deberta-v2", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "pooler_dropout": 0, + "pooler_hidden_act": "gelu", + "pooler_hidden_size": 32, + "pos_att_type": [ + "none" + ], + "position_biased_input": true, + "relative_attention": false, + "tie_word_embeddings": true, + "type_vocab_size": 16, + "vocab_size": 128001 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/edcab1a055d099bddf33c1ad78b95fd10128ada23735cbda28d65ff37615d4db/bc5d9c230cc9717f30b6.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/edcab1a055d099bddf33c1ad78b95fd10128ada23735cbda28d65ff37615d4db/bc5d9c230cc9717f30b6.json new file mode 100644 index 0000000000000000000000000000000000000000..ff7bf7b5da4c7ae0a3994e076f92d02081086cbe --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/edcab1a055d099bddf33c1ad78b95fd10128ada23735cbda28d65ff37615d4db/bc5d9c230cc9717f30b6.json @@ -0,0 +1,56 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-xlm-roberta", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "XLMRobertaForCausalLM" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "d_ff": 256, + "d_kv": 8, + "d_model": 64, + "dtype": "float32", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 256, + "initializer_range": 0.02, + "intermediate_size": 256, + "is_decoder": false, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 64, + "model_type": "xlm-roberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "xlm-roberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 2, + "num_decoder_layers": 2, + "num_heads": 2, + "num_hidden_layers": 2, + "num_layers": 2, + "output_past": true, + "position_embedding_type": "absolute", + "relative_attention_num_buckets": 32, + "tie_word_embeddings": true, + "type_vocab_size": 1, + "use_cache": true, + "vocab_size": 5002 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/eeec2031808ebd5ea4948e3a6ac212028bfe8d28e3fde385ec1a37d870f8b2c9/5b4bcc3bcea6babad275.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/eeec2031808ebd5ea4948e3a6ac212028bfe8d28e3fde385ec1a37d870f8b2c9/5b4bcc3bcea6babad275.json new file mode 100644 index 0000000000000000000000000000000000000000..9d6b4ec7c31759dd833e31d59b8ee8e4298bf0e0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/eeec2031808ebd5ea4948e3a6ac212028bfe8d28e3fde385ec1a37d870f8b2c9/5b4bcc3bcea6babad275.json @@ -0,0 +1,43 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DistilBertModel", + "_task": "question-answering", + "activation": "gelu", + "architectures": [ + "DistilBertModel" + ], + "attention_dropout": 0.1, + "dim": 32, + "dropout": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dim": 37, + "initializer_range": 0.02, + "max_position_embeddings": 512, + "model_type": "distilbert", + "n_heads": 4, + "n_layers": 5, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "distilbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "question-answering", + "tensor_parallel_size": 1 + }, + "qa_dropout": 0.1, + "seq_classif_dropout": 0.2, + "sinusoidal_pos_embds": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ef40bf078c9d608714e088b9b107f0e1dc42d53824cb83228f1504c91d61efd7/ab408a8549e55bde9441.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ef40bf078c9d608714e088b9b107f0e1dc42d53824cb83228f1504c91d61efd7/ab408a8549e55bde9441.json new file mode 100644 index 0000000000000000000000000000000000000000..72b20cec9b49e379620cdc385aa14a4b62e2a7f4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ef40bf078c9d608714e088b9b107f0e1dc42d53824cb83228f1504c91d61efd7/ab408a8549e55bde9441.json @@ -0,0 +1,105 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-Wav2Vec2Model", + "_task": "audio-xvector", + "activation_dropout": 0.1, + "adapter_attn_dim": null, + "adapter_kernel_size": 3, + "adapter_stride": 2, + "add_adapter": false, + "apply_spec_augment": true, + "architectures": [ + "Wav2Vec2Model" + ], + "attention_dropout": 0.1, + "classifier_proj_size": 256, + "codevector_dim": 256, + "contrastive_logits_temperature": 0.1, + "conv_bias": false, + "conv_dim": [ + 32, + 32, + 32 + ], + "conv_kernel": [ + 8, + 8, + 8 + ], + "conv_stride": [ + 4, + 4, + 4 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "diversity_loss_weight": 0.1, + "do_stable_layer_norm": false, + "dtype": "float32", + "feat_extract_activation": "gelu", + "feat_extract_dropout": 0.0, + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_quantizer_dropout": 0.0, + "final_dropout": 0.1, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_dropout_prob": 0.1, + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 20, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 2, + "mask_time_min_masks": 2, + "mask_time_prob": 0.5, + "model_type": "wav2vec2", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "wav2vec2", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_audio_sequence_length": 100000, + "static_batch_size": 1, + "task": "audio-xvector", + "tensor_parallel_size": 1 + }, + "num_adapter_layers": 1, + "num_attention_heads": 2, + "num_codevector_groups": 2, + "num_codevectors_per_group": 320, + "num_conv_pos_embedding_groups": 2, + "num_conv_pos_embeddings": 16, + "num_feat_extract_layers": 3, + "num_hidden_layers": 4, + "num_negatives": 100, + "output_hidden_size": 16, + "proj_codevector_dim": 256, + "tdnn_dilation": [ + 1, + 2 + ], + "tdnn_dim": [ + 32, + 32 + ], + "tdnn_kernel": [ + 5, + 3 + ], + "use_weighted_layer_sum": false, + "vocab_size": 32, + "xvector_output_dim": 32 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ef40bf078c9d608714e088b9b107f0e1dc42d53824cb83228f1504c91d61efd7/d97564fcad9dbbebc715.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ef40bf078c9d608714e088b9b107f0e1dc42d53824cb83228f1504c91d61efd7/d97564fcad9dbbebc715.json new file mode 100644 index 0000000000000000000000000000000000000000..2bb6f81fbaa5822a8a3be133ce26ff5568f8562b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ef40bf078c9d608714e088b9b107f0e1dc42d53824cb83228f1504c91d61efd7/d97564fcad9dbbebc715.json @@ -0,0 +1,105 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-Wav2Vec2Model", + "_task": "audio-xvector", + "activation_dropout": 0.1, + "adapter_attn_dim": null, + "adapter_kernel_size": 3, + "adapter_stride": 2, + "add_adapter": false, + "apply_spec_augment": true, + "architectures": [ + "Wav2Vec2Model" + ], + "attention_dropout": 0.1, + "classifier_proj_size": 256, + "codevector_dim": 256, + "contrastive_logits_temperature": 0.1, + "conv_bias": false, + "conv_dim": [ + 32, + 32, + 32 + ], + "conv_kernel": [ + 8, + 8, + 8 + ], + "conv_stride": [ + 4, + 4, + 4 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "diversity_loss_weight": 0.1, + "do_stable_layer_norm": false, + "dtype": "float32", + "feat_extract_activation": "gelu", + "feat_extract_dropout": 0.0, + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_quantizer_dropout": 0.0, + "final_dropout": 0.1, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_dropout_prob": 0.1, + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 20, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 2, + "mask_time_min_masks": 2, + "mask_time_prob": 0.5, + "model_type": "wav2vec2", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "wav2vec2", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_audio_sequence_length": 100000, + "static_batch_size": 1, + "task": "audio-xvector", + "tensor_parallel_size": 1 + }, + "num_adapter_layers": 1, + "num_attention_heads": 2, + "num_codevector_groups": 2, + "num_codevectors_per_group": 320, + "num_conv_pos_embedding_groups": 2, + "num_conv_pos_embeddings": 16, + "num_feat_extract_layers": 3, + "num_hidden_layers": 4, + "num_negatives": 100, + "output_hidden_size": 16, + "proj_codevector_dim": 256, + "tdnn_dilation": [ + 1, + 2 + ], + "tdnn_dim": [ + 32, + 32 + ], + "tdnn_kernel": [ + 5, + 3 + ], + "use_weighted_layer_sum": false, + "vocab_size": 32, + "xvector_output_dim": 32 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/electra/hf-internal-testing/tiny-random-ElectraModel/3a6a997eb9ac299901af.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/electra/hf-internal-testing/tiny-random-ElectraModel/3a6a997eb9ac299901af.json new file mode 100644 index 0000000000000000000000000000000000000000..28d261a588d32fda89eab18b80afa62e5025ab51 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/electra/hf-internal-testing/tiny-random-ElectraModel/3a6a997eb9ac299901af.json @@ -0,0 +1,49 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ElectraModel", + "_task": "token-classification", + "architectures": [ + "ElectraModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "electra", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "electra", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "summary_activation": "gelu", + "summary_last_dropout": 0.1, + "summary_type": "first", + "summary_use_proj": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f0d4d2b20f6e94a6c6df05087dc9bd06b4ee124b34d26b0cbe6f45cf78d46132/b57789d2dd06cc907b15.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f0d4d2b20f6e94a6c6df05087dc9bd06b4ee124b34d26b0cbe6f45cf78d46132/b57789d2dd06cc907b15.json new file mode 100644 index 0000000000000000000000000000000000000000..ac2caf9ada8ba64d47140234e893160ada19efd4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f0d4d2b20f6e94a6c6df05087dc9bd06b4ee124b34d26b0cbe6f45cf78d46132/b57789d2dd06cc907b15.json @@ -0,0 +1,43 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DistilBertModel", + "_task": "feature-extraction", + "activation": "gelu", + "architectures": [ + "DistilBertModel" + ], + "attention_dropout": 0.1, + "dim": 32, + "dropout": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dim": 37, + "initializer_range": 0.02, + "max_position_embeddings": 512, + "model_type": "distilbert", + "n_heads": 4, + "n_layers": 5, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "distilbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "qa_dropout": 0.1, + "seq_classif_dropout": 0.2, + "sinusoidal_pos_embds": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f41b36d9890fc8785794fe0fa12d889ccf856725cd80499af03ee264ce092611/9db05a6c01395b8bfb6d.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f41b36d9890fc8785794fe0fa12d889ccf856725cd80499af03ee264ce092611/9db05a6c01395b8bfb6d.json new file mode 100644 index 0000000000000000000000000000000000000000..58bbeb5de208035aae3fc6833a125fc51763a50e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f41b36d9890fc8785794fe0fa12d889ccf856725cd80499af03ee264ce092611/9db05a6c01395b8bfb6d.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-flaubert", + "_task": "feature-extraction", + "architectures": [ + "FlaubertModel" + ], + "asm": false, + "attention_dropout": 0.1, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "layerdrop": 0.0, + "mask_index": 5, + "mask_token_id": 0, + "max_position_embeddings": 512, + "model_type": "flaubert", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "flaubert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "pre_norm": false, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "tie_word_embeddings": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": null, + "vocab_size": 68729 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f41b36d9890fc8785794fe0fa12d889ccf856725cd80499af03ee264ce092611/f92462eafc58029b072a.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f41b36d9890fc8785794fe0fa12d889ccf856725cd80499af03ee264ce092611/f92462eafc58029b072a.json new file mode 100644 index 0000000000000000000000000000000000000000..2d73eb13ffc3948ff054a7b92f97982b32f5a30a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f41b36d9890fc8785794fe0fa12d889ccf856725cd80499af03ee264ce092611/f92462eafc58029b072a.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-flaubert", + "_task": "feature-extraction", + "architectures": [ + "FlaubertModel" + ], + "asm": false, + "attention_dropout": 0.1, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "layerdrop": 0.0, + "mask_index": 5, + "mask_token_id": 0, + "max_position_embeddings": 512, + "model_type": "flaubert", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "flaubert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "pre_norm": false, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "tie_word_embeddings": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": null, + "vocab_size": 68729 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f44c11068e07b08e05b4d7bdb723c014b64e21685696fdfb53b0681d8ec3ad7e/8eac5b4b1832b3bbe461.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f44c11068e07b08e05b4d7bdb723c014b64e21685696fdfb53b0681d8ec3ad7e/8eac5b4b1832b3bbe461.json new file mode 100644 index 0000000000000000000000000000000000000000..9ec123a8b7c53c5138cb4d3bd77630d8e4abbfb1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f44c11068e07b08e05b4d7bdb723c014b64e21685696fdfb53b0681d8ec3ad7e/8eac5b4b1832b3bbe461.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 16, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f44c11068e07b08e05b4d7bdb723c014b64e21685696fdfb53b0681d8ec3ad7e/b5ac6ae61a21f1d9ab51.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f44c11068e07b08e05b4d7bdb723c014b64e21685696fdfb53b0681d8ec3ad7e/b5ac6ae61a21f1d9ab51.json new file mode 100644 index 0000000000000000000000000000000000000000..f814ca3e6f1556d69583e4c46473da06c182ec92 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f44c11068e07b08e05b4d7bdb723c014b64e21685696fdfb53b0681d8ec3ad7e/b5ac6ae61a21f1d9ab51.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 16, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f44c11068e07b08e05b4d7bdb723c014b64e21685696fdfb53b0681d8ec3ad7e/c9f4856b4ed4d8ae2009.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f44c11068e07b08e05b4d7bdb723c014b64e21685696fdfb53b0681d8ec3ad7e/c9f4856b4ed4d8ae2009.json new file mode 100644 index 0000000000000000000000000000000000000000..d33a61abae0622bec8401fcf3fc9b5639da5df45 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f44c11068e07b08e05b4d7bdb723c014b64e21685696fdfb53b0681d8ec3ad7e/c9f4856b4ed4d8ae2009.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": false, + "instance_type": null, + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 16, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f44c11068e07b08e05b4d7bdb723c014b64e21685696fdfb53b0681d8ec3ad7e/d616fb5c6763cff60f9e.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f44c11068e07b08e05b4d7bdb723c014b64e21685696fdfb53b0681d8ec3ad7e/d616fb5c6763cff60f9e.json new file mode 100644 index 0000000000000000000000000000000000000000..47b93492dd5774c86e4ba1b4487f829b849c90ef --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f44c11068e07b08e05b4d7bdb723c014b64e21685696fdfb53b0681d8ec3ad7e/d616fb5c6763cff60f9e.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f44c11068e07b08e05b4d7bdb723c014b64e21685696fdfb53b0681d8ec3ad7e/ee1997fce5adbc158450.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f44c11068e07b08e05b4d7bdb723c014b64e21685696fdfb53b0681d8ec3ad7e/ee1997fce5adbc158450.json new file mode 100644 index 0000000000000000000000000000000000000000..86fda2208798bf99e4d8773f391ac21b438ffe1e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f44c11068e07b08e05b4d7bdb723c014b64e21685696fdfb53b0681d8ec3ad7e/ee1997fce5adbc158450.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f452d48e2925e6fd0e0f2b8b2fa5b3e11e9a412e158a5fdc8dfbb701ebe0297d/b3e62ce452071e89e41f.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f452d48e2925e6fd0e0f2b8b2fa5b3e11e9a412e158a5fdc8dfbb701ebe0297d/b3e62ce452071e89e41f.json new file mode 100644 index 0000000000000000000000000000000000000000..b64c010e90a6f2b525094473b6551213ab1ebd28 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f452d48e2925e6fd0e0f2b8b2fa5b3e11e9a412e158a5fdc8dfbb701ebe0297d/b3e62ce452071e89e41f.json @@ -0,0 +1,41 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MPNetModel", + "_task": "feature-extraction", + "architectures": [ + "MPNetModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 64, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mpnet", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mpnet", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "relative_attention_num_buckets": 32, + "vocab_size": 1125 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f52f7193577475776359686cadf5ffc17f56aeb372f41ba07f331d53730877cb/1e4a5b736de5725271bd.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f52f7193577475776359686cadf5ffc17f56aeb372f41ba07f331d53730877cb/1e4a5b736de5725271bd.json new file mode 100644 index 0000000000000000000000000000000000000000..cec4392a2975d4bb9beaf11523bedbc5d18db8be --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f52f7193577475776359686cadf5ffc17f56aeb372f41ba07f331d53730877cb/1e4a5b736de5725271bd.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MobileBertModel", + "_task": "text-classification", + "architectures": [ + "MobileBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_activation": true, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 37, + "intra_bottleneck_size": 128, + "key_query_shared_bottleneck": true, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mobilebert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mobilebert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "normalization_type": "no_norm", + "num_attention_heads": 4, + "num_feedforward_networks": 4, + "num_hidden_layers": 5, + "trigram_input": true, + "true_hidden_size": 128, + "type_vocab_size": 16, + "use_bottleneck": true, + "use_bottleneck_attention": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f91ae7c44e6189d18079e9b9580bb4be0167671bb35fa804b9c901d01e300951/de171fb58933d3ee5c0e.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f91ae7c44e6189d18079e9b9580bb4be0167671bb35fa804b9c901d01e300951/de171fb58933d3ee5c0e.json new file mode 100644 index 0000000000000000000000000000000000000000..6ac3b11805a74f230e779867b9be9c331996bacc --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/f91ae7c44e6189d18079e9b9580bb4be0167671bb35fa804b9c901d01e300951/de171fb58933d3ee5c0e.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-DistilBertModel", + "_task": "token-classification", + "activation": "gelu", + "architectures": [ + "DistilBertModel" + ], + "attention_dropout": 0.1, + "dim": 32, + "dropout": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dim": 37, + "initializer_range": 0.02, + "max_position_embeddings": 512, + "model_type": "distilbert", + "n_heads": 4, + "n_layers": 5, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "distilbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "qa_dropout": 0.1, + "seq_classif_dropout": 0.2, + "sinusoidal_pos_embds": false, + "tie_word_embeddings": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fcd4d47a02760f0d71f89abeff3a8bf21d3789df1de474fdd08d62f4c7645339/0502f63e32ca06896fd7.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fcd4d47a02760f0d71f89abeff3a8bf21d3789df1de474fdd08d62f4c7645339/0502f63e32ca06896fd7.json new file mode 100644 index 0000000000000000000000000000000000000000..115068000eb37b181816d3c8b0f7ee71ca5ec619 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fcd4d47a02760f0d71f89abeff3a8bf21d3789df1de474fdd08d62f4c7645339/0502f63e32ca06896fd7.json @@ -0,0 +1,45 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-camembert", + "_task": "token-classification", + "architectures": [ + "CamembertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "camembert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "camembert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd53ce61a9f5b2d680ee14f16ba03497300a018350cb6ecd4c4e25fe7478e8d6/19fc1eea83d4ea79dc6b.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd53ce61a9f5b2d680ee14f16ba03497300a018350cb6ecd4c4e25fe7478e8d6/19fc1eea83d4ea79dc6b.json new file mode 100644 index 0000000000000000000000000000000000000000..1a4eed462a9a37ab0ceccb2f7a4365d5f009887b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd53ce61a9f5b2d680ee14f16ba03497300a018350cb6ecd4c4e25fe7478e8d6/19fc1eea83d4ea79dc6b.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MobileBertModel", + "_task": "fill-mask", + "architectures": [ + "MobileBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_activation": true, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 37, + "intra_bottleneck_size": 128, + "key_query_shared_bottleneck": true, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mobilebert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mobilebert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "normalization_type": "no_norm", + "num_attention_heads": 4, + "num_feedforward_networks": 4, + "num_hidden_layers": 5, + "tie_word_embeddings": true, + "trigram_input": true, + "true_hidden_size": 128, + "type_vocab_size": 16, + "use_bottleneck": true, + "use_bottleneck_attention": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd53ce61a9f5b2d680ee14f16ba03497300a018350cb6ecd4c4e25fe7478e8d6/9366c4ab5421c5d229c0.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd53ce61a9f5b2d680ee14f16ba03497300a018350cb6ecd4c4e25fe7478e8d6/9366c4ab5421c5d229c0.json new file mode 100644 index 0000000000000000000000000000000000000000..66523a54b694d0c6b4038a5288a6e0397958478d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd53ce61a9f5b2d680ee14f16ba03497300a018350cb6ecd4c4e25fe7478e8d6/9366c4ab5421c5d229c0.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MobileBertModel", + "_task": "fill-mask", + "architectures": [ + "MobileBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_activation": true, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 37, + "intra_bottleneck_size": 128, + "key_query_shared_bottleneck": true, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mobilebert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mobilebert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "normalization_type": "no_norm", + "num_attention_heads": 4, + "num_feedforward_networks": 4, + "num_hidden_layers": 5, + "tie_word_embeddings": true, + "trigram_input": true, + "true_hidden_size": 128, + "type_vocab_size": 16, + "use_bottleneck": true, + "use_bottleneck_attention": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd73bab427ebb07a8d5b2acc80f46487dc0d09e672da5d87c0fd201b9764f64b/6841a7152ac1126bd8c1.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd73bab427ebb07a8d5b2acc80f46487dc0d09e672da5d87c0fd201b9764f64b/6841a7152ac1126bd8c1.json new file mode 100644 index 0000000000000000000000000000000000000000..3380324dce764e4c7a1da4690be06eb03f7cd50c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd73bab427ebb07a8d5b2acc80f46487dc0d09e672da5d87c0fd201b9764f64b/6841a7152ac1126bd8c1.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-flaubert", + "_task": "fill-mask", + "architectures": [ + "FlaubertModel" + ], + "asm": false, + "attention_dropout": 0.1, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "layerdrop": 0.0, + "mask_index": 5, + "mask_token_id": 0, + "max_position_embeddings": 512, + "model_type": "flaubert", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "flaubert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "pre_norm": false, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "tie_word_embeddings": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": null, + "vocab_size": 68729 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd73bab427ebb07a8d5b2acc80f46487dc0d09e672da5d87c0fd201b9764f64b/eec97a04f7ab1ab5824b.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd73bab427ebb07a8d5b2acc80f46487dc0d09e672da5d87c0fd201b9764f64b/eec97a04f7ab1ab5824b.json new file mode 100644 index 0000000000000000000000000000000000000000..bf5e5564cdb43eabff540d03524186938d8b3813 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd73bab427ebb07a8d5b2acc80f46487dc0d09e672da5d87c0fd201b9764f64b/eec97a04f7ab1ab5824b.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-flaubert", + "_task": "fill-mask", + "architectures": [ + "FlaubertModel" + ], + "asm": false, + "attention_dropout": 0.1, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "layerdrop": 0.0, + "mask_index": 5, + "mask_token_id": 0, + "max_position_embeddings": 512, + "model_type": "flaubert", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "flaubert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "pre_norm": false, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "tie_word_embeddings": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": null, + "vocab_size": 68729 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/073ff0443351b69dfa3f.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/073ff0443351b69dfa3f.json new file mode 100644 index 0000000000000000000000000000000000000000..45206efd0ab4453d01a5deeb0275edf7311f0b75 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/073ff0443351b69dfa3f.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": false, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 16, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/171fd0cd6b57b3dc43b1.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/171fd0cd6b57b3dc43b1.json new file mode 100644 index 0000000000000000000000000000000000000000..87a19bda8a6fd4b7ea2d5703864f188df2603d75 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/171fd0cd6b57b3dc43b1.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": false, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/63456e65ffe416736f2e.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/63456e65ffe416736f2e.json new file mode 100644 index 0000000000000000000000000000000000000000..abce0661707bbd10646a24e4ce86861a727c5536 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/63456e65ffe416736f2e.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": false, + "instance_type": "trn1n", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 16, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/678a12839a33d698635c.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/678a12839a33d698635c.json new file mode 100644 index 0000000000000000000000000000000000000000..bd303aa3bd1674a1c8149d3627b2c9b1649d038d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/678a12839a33d698635c.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": false, + "instance_type": null, + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "3", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 16, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/7770ed2638832ac46854.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/7770ed2638832ac46854.json new file mode 100644 index 0000000000000000000000000000000000000000..c4d7927aba472f517c97c7609ed749dacb3a6793 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/7770ed2638832ac46854.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/8f48534743910791837b.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/8f48534743910791837b.json new file mode 100644 index 0000000000000000000000000000000000000000..996e3be1336452028cafbd0af623fa88f42b89a4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/8f48534743910791837b.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Jingya/tiny-random-bert-remote-code", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/90f06329a6297dffed44.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/90f06329a6297dffed44.json new file mode 100644 index 0000000000000000000000000000000000000000..4ae88d7336150e62a174114018057afcf4eb0a63 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/90f06329a6297dffed44.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": false, + "instance_type": null, + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 16, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/b0ac093c2ed068b72bf8.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/b0ac093c2ed068b72bf8.json new file mode 100644 index 0000000000000000000000000000000000000000..33e8bc397d1c7d104ae8af37d066c7a706179c9e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/b0ac093c2ed068b72bf8.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/e1672d503f2e0fcb6457.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/e1672d503f2e0fcb6457.json new file mode 100644 index 0000000000000000000000000000000000000000..ddaef6f9bd9874e06d8e27ba29545032f7ab5950 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/e1672d503f2e0fcb6457.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": false, + "instance_type": null, + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 16, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/e1b5afd6aa67871960ac.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/e1b5afd6aa67871960ac.json new file mode 100644 index 0000000000000000000000000000000000000000..9706ceb2d0835532b5a08ba813b5683585cc7e7b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/e1b5afd6aa67871960ac.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": false, + "instance_type": null, + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "1", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 16, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/e346c2113e71cb07d7c3.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/e346c2113e71cb07d7c3.json new file mode 100644 index 0000000000000000000000000000000000000000..bfc55a19d7dc479034862351675d505a2e7bba44 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/e346c2113e71cb07d7c3.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": false, + "instance_type": "inf2", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 16, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/f46c9f7706d8db58070e.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/f46c9f7706d8db58070e.json new file mode 100644 index 0000000000000000000000000000000000000000..97082a22ef8299bb23087189506ee9cd1a05399a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fd8454e74a692ad75c465c845bb5e4e27fb2d103aa77fb6fbbca5c2b0aa2b870/f46c9f7706d8db58070e.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-BertModel", + "_task": "text-classification", + "add_cross_attention": false, + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": false, + "instance_type": "trn2", + "int_dtype": "int64", + "model_type": "bert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 16, + "task": "text-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fe6c7e870fe2abc6aff8f07ea88979e7c20f02f59b478d412b691f3164859a8b/0d3b88ab34257c5117d8.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fe6c7e870fe2abc6aff8f07ea88979e7c20f02f59b478d412b691f3164859a8b/0d3b88ab34257c5117d8.json new file mode 100644 index 0000000000000000000000000000000000000000..69ce853747c86e5c55188c7bb704ebae8d805b50 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fe6c7e870fe2abc6aff8f07ea88979e7c20f02f59b478d412b691f3164859a8b/0d3b88ab34257c5117d8.json @@ -0,0 +1,90 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/gemma-3-270m-it", + "_sliding_window_pattern": 6, + "_task": "text-generation", + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "dtype": "bfloat16", + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 640, + "initializer_range": 0.02, + "intermediate_size": 2048, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/gemma-3-270m-it", + "checkpoint_revision": "23cf460f6bb16954176b3ddcc8d4f250501458a9", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "full_attention": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_attention": { + "rope_theta": 10000.0, + "rope_type": "default" + } + }, + "sliding_window": 512, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_bidirectional_attention": false, + "use_cache": true, + "vocab_size": 262144 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fe9f58f4ee40c5cc18ddead5fefcc731172ac005cbebd455ec3d3f98d6b2b493/3f180c846b03b74ef15a.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fe9f58f4ee40c5cc18ddead5fefcc731172ac005cbebd455ec3d3f98d6b2b493/3f180c846b03b74ef15a.json new file mode 100644 index 0000000000000000000000000000000000000000..ee5279f8cddf2be2a3559363fb91777ecb944dfb --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/fe9f58f4ee40c5cc18ddead5fefcc731172ac005cbebd455ec3d3f98d6b2b493/3f180c846b03b74ef15a.json @@ -0,0 +1,46 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-ConvBertModel", + "_task": "fill-mask", + "architectures": [ + "ConvBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "conv_kernel_size": 9, + "dtype": "float32", + "embedding_size": 768, + "head_ratio": 2, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "convbert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "convbert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_groups": 1, + "num_hidden_layers": 5, + "type_vocab_size": 16, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ff145946ddcb51acedbcc254154381665721de21c073353484bc3b5e9697f2d2/94661956f819d157a15d.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ff145946ddcb51acedbcc254154381665721de21c073353484bc3b5e9697f2d2/94661956f819d157a15d.json new file mode 100644 index 0000000000000000000000000000000000000000..4311c2c1f76655ad15281a2070f0bb4720784f88 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ff145946ddcb51acedbcc254154381665721de21c073353484bc3b5e9697f2d2/94661956f819d157a15d.json @@ -0,0 +1,46 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-AlbertModel", + "_task": "feature-extraction", + "architectures": [ + "AlbertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 128, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 36, + "initializer_range": 0.02, + "inner_group_num": 1, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "albert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "albert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 6, + "num_hidden_groups": 6, + "num_hidden_layers": 6, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "vocab_size": 30000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ff3a554ababebc902e7dd2d0f9782f320130dd11fb38f56a086f71970c9f9ff6/906f0d9048935b4744cc.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ff3a554ababebc902e7dd2d0f9782f320130dd11fb38f56a086f71970c9f9ff6/906f0d9048935b4744cc.json new file mode 100644 index 0000000000000000000000000000000000000000..c21894d14db740adceab666e729d833f59f97922 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ff3a554ababebc902e7dd2d0f9782f320130dd11fb38f56a086f71970c9f9ff6/906f0d9048935b4744cc.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RobertaModel", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "RobertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1024 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ff3a554ababebc902e7dd2d0f9782f320130dd11fb38f56a086f71970c9f9ff6/aec70d6c6373e36d4401.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ff3a554ababebc902e7dd2d0f9782f320130dd11fb38f56a086f71970c9f9ff6/aec70d6c6373e36d4401.json new file mode 100644 index 0000000000000000000000000000000000000000..494a2e19f711b133b4c6e3fe036a7afd174d58e8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/ff3a554ababebc902e7dd2d0f9782f320130dd11fb38f56a086f71970c9f9ff6/aec70d6c6373e36d4401.json @@ -0,0 +1,47 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RobertaModel", + "_task": "feature-extraction", + "add_cross_attention": false, + "architectures": [ + "RobertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "is_decoder": false, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "tie_word_embeddings": true, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1024 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/flaubert/flaubert/flaubert_small_cased/1be343b49fdcf56bc70f.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/flaubert/flaubert/flaubert_small_cased/1be343b49fdcf56bc70f.json new file mode 100644 index 0000000000000000000000000000000000000000..c3093ff46fe3650a6135ff0adbe1c7563f0bab56 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/flaubert/flaubert/flaubert_small_cased/1be343b49fdcf56bc70f.json @@ -0,0 +1,98 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "flaubert/flaubert_small_cased", + "_task": "token-classification", + "amp": 1, + "architectures": [ + "FlaubertWithLMHeadModel" + ], + "asm": false, + "attention_dropout": 0.1, + "bos_index": 0, + "bptt": 512, + "causal": false, + "clip_grad_norm": 5, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 512, + "embed_init_std": 0.02209708691207961, + "encoder_only": true, + "end_n_top": 5, + "eos_index": 1, + "fp16": true, + "gelu_activation": true, + "group_by_size": true, + "id2lang": { + "0": "fr" + }, + "init_std": 0.02, + "is_encoder": true, + "lang2id": { + "fr": 0 + }, + "lang_id": 0, + "langs": [ + "fr" + ], + "layer_norm_eps": 1e-06, + "layerdrop": 0.2, + "lg_sampling_factor": -1, + "lgs": "fr", + "mask_index": 5, + "mask_token_id": 0, + "max_batch_size": 0, + "max_position_embeddings": 512, + "max_vocab": -1, + "mlm_steps": [ + [ + "fr", + null + ] + ], + "model_type": "flaubert", + "n_heads": 8, + "n_langs": 1, + "n_layers": 6, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "flaubert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "pad_index": 2, + "pre_norm": true, + "sample_alpha": 0, + "share_inout_emb": true, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "first", + "summary_use_proj": true, + "tokens_per_batch": -1, + "unk_index": 3, + "use_lang_emb": true, + "vocab_size": 68729, + "word_blank": 0, + "word_dropout": 0, + "word_keep": 0.1, + "word_mask": 0.8, + "word_mask_keep_rand": "0.8,0.1,0.1", + "word_pred": 0.15, + "word_rand": 0.1, + "word_shuffle": 0 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/flaubert/hf-internal-testing/tiny-random-flaubert/ee4fc48e52b39ca7deba.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/flaubert/hf-internal-testing/tiny-random-flaubert/ee4fc48e52b39ca7deba.json new file mode 100644 index 0000000000000000000000000000000000000000..f0329bbcfe3a31e2bd8436293603530fa642fc32 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/flaubert/hf-internal-testing/tiny-random-flaubert/ee4fc48e52b39ca7deba.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-flaubert", + "_task": "token-classification", + "architectures": [ + "FlaubertModel" + ], + "asm": false, + "attention_dropout": 0.1, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "layerdrop": 0.0, + "mask_index": 5, + "mask_token_id": 0, + "max_position_embeddings": 512, + "model_type": "flaubert", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "flaubert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "pre_norm": false, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "tie_word_embeddings": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": null, + "vocab_size": 68729 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/gemma3/tengomucho/tiny-random-gemma-3-vlm/8fd07da0df2a2f31aff8.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/gemma3/tengomucho/tiny-random-gemma-3-vlm/8fd07da0df2a2f31aff8.json new file mode 100644 index 0000000000000000000000000000000000000000..fbcae5e06f1a1b3b813a15cf8d66832021086c0a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/gemma3/tengomucho/tiny-random-gemma-3-vlm/8fd07da0df2a2f31aff8.json @@ -0,0 +1,107 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "tengomucho/tiny-random-gemma-3-vlm", + "_task": "image-text-to-text", + "architectures": [ + "Gemma3ForConditionalGeneration" + ], + "boi_token_index": 255999, + "dtype": "bfloat16", + "eoi_token_index": 256000, + "image_token_index": 262144, + "initializer_range": 0.02, + "mm_tokens_per_image": 256, + "model_type": "gemma3", + "neuron": { + "_serialized_key": "NxDVLMNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "tengomucho/tiny-random-gemma-3-vlm", + "checkpoint_revision": "880db0f4a0e1000cec5193ea9a93c30ce425c0e5", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "image_seq_len": 256, + "image_size": 896, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 2048, + "max_num_images": 5, + "max_topk": 256, + "n_active_tokens": 2048, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 2048, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_key_value_heads": 2, + "text_config": { + "_sliding_window_pattern": 2, + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "dtype": "bfloat16", + "eos_token_id": 1, + "final_logit_softcapping": null, + "head_dim": 64, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 128, + "initializer_range": 0.02, + "intermediate_size": 256, + "layer_types": [ + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "model_type": "gemma3_text", + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "pad_token_id": 0, + "query_pre_attn_scalar": 168, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "full_attention": { + "factor": 8.0, + "rope_theta": 1000000.0, + "rope_type": "linear" + }, + "sliding_attention": { + "rope_theta": 10000.0, + "rope_type": "default" + } + }, + "sliding_window": 1024, + "sliding_window_pattern": 2, + "tie_word_embeddings": true, + "use_bidirectional_attention": false, + "use_cache": true, + "vocab_size": 262208 + }, + "tie_word_embeddings": true, + "vision_config": { + "attention_dropout": 0.0, + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 32, + "image_size": 896, + "intermediate_size": 128, + "layer_norm_eps": 1e-06, + "model_type": "siglip_vision_model", + "num_attention_heads": 2, + "num_channels": 3, + "num_hidden_layers": 2, + "patch_size": 14, + "vision_use_head": false + } +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/gemma3_text/unsloth/gemma-3-270m-it/0d3b88ab34257c5117d8.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/gemma3_text/unsloth/gemma-3-270m-it/0d3b88ab34257c5117d8.json new file mode 100644 index 0000000000000000000000000000000000000000..69ce853747c86e5c55188c7bb704ebae8d805b50 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/gemma3_text/unsloth/gemma-3-270m-it/0d3b88ab34257c5117d8.json @@ -0,0 +1,90 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/gemma-3-270m-it", + "_sliding_window_pattern": 6, + "_task": "text-generation", + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "dtype": "bfloat16", + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 640, + "initializer_range": 0.02, + "intermediate_size": 2048, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/gemma-3-270m-it", + "checkpoint_revision": "23cf460f6bb16954176b3ddcc8d4f250501458a9", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "full_attention": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_attention": { + "rope_theta": 10000.0, + "rope_type": "default" + } + }, + "sliding_window": 512, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_bidirectional_attention": false, + "use_cache": true, + "vocab_size": 262144 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/643554f31cfe71c82427.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/643554f31cfe71c82427.json new file mode 100644 index 0000000000000000000000000000000000000000..2e191f335e4f6b9b325fde4756002bf0222669f1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/643554f31cfe71c82427.json @@ -0,0 +1,61 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "dtype": "float32", + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 10000.0, + "rope_type": "default" + }, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/idefics3/HuggingFaceTB/SmolVLM-256M-Instruct/13df271b67157400bb7d.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/idefics3/HuggingFaceTB/SmolVLM-256M-Instruct/13df271b67157400bb7d.json new file mode 100644 index 0000000000000000000000000000000000000000..84484addd42f16fd4371713057eb9bcc76500b00 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/idefics3/HuggingFaceTB/SmolVLM-256M-Instruct/13df271b67157400bb7d.json @@ -0,0 +1,225 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolVLM-256M-Instruct", + "_task": "image-text-to-text", + "architectures": [ + "Idefics3ForConditionalGeneration" + ], + "dtype": "bfloat16", + "image_token_id": 49190, + "model_type": "idefics3", + "neuron": { + "_serialized_key": "NxDVLMNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolVLM-256M-Instruct", + "checkpoint_revision": "7e3e67edbbed1bf9888184d9df282b700a323964", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "image_seq_len": 64, + "image_size": 512, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 2048, + "max_num_images": 17, + "max_topk": 256, + "n_active_tokens": 2048, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 1024, + "sequence_length": 2048, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "scale_factor": 4, + "text_config": { + "_attn_implementation_autoset": false, + "_flash_attn_2_enabled": true, + "_name_or_path": "None", + "add_cross_attention": false, + "architectures": [ + "VLlama3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 2, + "finetuning_task": null, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 576, + "initializer_range": 0.041666666666666664, + "intermediate_size": 1536, + "is_decoder": false, + "is_llama_config": true, + "max_position_embeddings": 8192, + "mlp_bias": false, + "model_type": "llama", + "neftune_noise_alpha": 0.0, + "num_attention_heads": 9, + "num_hidden_layers": 30, + "num_key_value_heads": 3, + "pad_token_id": 2, + "perceiver_config": { + "_attn_implementation_autoset": false, + "_name_or_path": "", + "add_cross_attention": false, + "architectures": null, + "attention_dropout": 0.0, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "chunk_size_feed_forward": 0, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "diversity_penalty": 0.0, + "do_sample": false, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": null, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "silu", + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "is_decoder": false, + "is_encoder_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "length_penalty": 1.0, + "max_length": 20, + "min_length": 0, + "model_type": "vllama3", + "no_repeat_ngram_size": 0, + "num_beam_groups": 1, + "num_beams": 1, + "num_key_value_heads": 1, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": null, + "prefix": null, + "problem_type": null, + "pruned_heads": {}, + "qk_layer_norms_perceiver": false, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "resampler_depth": 6, + "resampler_head_dim": 96, + "resampler_n_heads": 16, + "resampler_n_latents": 64, + "return_dict": true, + "return_dict_in_generate": false, + "sep_token_id": null, + "suppress_tokens": null, + "task_specific_params": null, + "temperature": 1.0, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": null, + "torchscript": false, + "transformers_version": "4.46.0", + "typical_p": 1.0, + "use_bfloat16": false + }, + "pixel_shuffle_factor": 4, + "prefix": null, + "pretraining_tp": 1, + "pruned_heads": {}, + "qk_layer_norms": false, + "rms_norm_eps": 1e-05, + "rope_interleaved": false, + "rope_parameters": { + "rope_theta": 100000, + "rope_type": "default" + }, + "sep_token_id": null, + "task_specific_params": null, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": false, + "tokenizer_class": null, + "torchscript": false, + "transformers.js_config": { + "kv_cache_dtype": { + "fp16": "float16", + "q4f16": "float16" + } + }, + "use_bfloat16": false, + "use_cache": true, + "use_resampler": false, + "vocab_size": 49280 + }, + "tie_word_embeddings": false, + "transformers.js_config": { + "kv_cache_dtype": { + "fp16": "float16", + "q4f16": "float16" + } + }, + "use_cache": true, + "vision_config": { + "_attn_implementation_autoset": false, + "add_cross_attention": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "eos_token_id": null, + "finetuning_task": null, + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 768, + "image_size": 512, + "initializer_range": 0.02, + "intermediate_size": 3072, + "is_decoder": false, + "layer_norm_eps": 1e-06, + "max_image_size": { + "longest_edge": 512 + }, + "model_type": "idefics3_vision", + "num_attention_heads": 12, + "num_channels": 3, + "num_hidden_layers": 12, + "pad_token_id": null, + "patch_size": 16, + "prefix": null, + "pruned_heads": {}, + "sep_token_id": null, + "size": { + "longest_edge": 2048 + }, + "task_specific_params": null, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": false, + "tokenizer_class": null, + "torchscript": false, + "use_base_siglip": true, + "use_bfloat16": false + }, + "vocab_size": 49280 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama/llamafactory/tiny-random-Llama-3/001735c65eb958259350.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama/llamafactory/tiny-random-Llama-3/001735c65eb958259350.json new file mode 100644 index 0000000000000000000000000000000000000000..cc262a23261237c839137e7b16178f00ba27a281 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama/llamafactory/tiny-random-Llama-3/001735c65eb958259350.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "float16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 512, + "max_topk": 256, + "n_active_tokens": 512, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 512, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_theta": 500000.0, + "rope_type": "llama3" + }, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama/unsloth/Llama-3.2-1B-Instruct/efbf3a0d9f80027e2470.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama/unsloth/Llama-3.2-1B-Instruct/efbf3a0d9f80027e2470.json new file mode 100644 index 0000000000000000000000000000000000000000..720e277a58cb5d68a1b9240905916d58fee26f2b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama/unsloth/Llama-3.2-1B-Instruct/efbf3a0d9f80027e2470.json @@ -0,0 +1,64 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_theta": 500000.0, + "rope_type": "llama3" + }, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama4/llamafactory/tiny-random-Llama-4/a1fa39f3b67695d6132f.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama4/llamafactory/tiny-random-Llama-4/a1fa39f3b67695d6132f.json new file mode 100644 index 0000000000000000000000000000000000000000..5267681df0ef17435db267225dfb226bbf36d7dd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama4/llamafactory/tiny-random-Llama-4/a1fa39f3b67695d6132f.json @@ -0,0 +1,127 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-4", + "_task": "text-generation", + "architectures": [ + "Llama4ForConditionalGeneration" + ], + "boi_token_index": 200080, + "dtype": "float32", + "eoi_token_index": 200081, + "image_token_index": 200092, + "model_type": "llama4", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-4", + "checkpoint_revision": "40216585996ab548819dea4cd1d46e0c0c1093d9", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "text_config": { + "_attn_implementation_autoset": true, + "attention_bias": false, + "attention_chunk_size": 8192, + "attention_dropout": 0.0, + "attn_scale": 0.1, + "attn_temperature_tuning": true, + "bos_token_id": 1, + "dtype": "float32", + "eos_token_id": 2, + "floor_scale": 8192, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 512, + "initializer_range": 0.02, + "interleave_moe_layer_step": 1, + "intermediate_size": 1024, + "intermediate_size_mlp": 1024, + "layer_types": [ + "chunked_attention", + "chunked_attention", + "chunked_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "model_type": "llama4_text", + "moe_layers": [ + 0, + 1, + 2, + 3 + ], + "no_rope_layer_interval": 4, + "no_rope_layers": [ + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 8, + "num_experts_per_tok": 1, + "num_hidden_layers": 4, + "num_key_value_heads": 2, + "num_local_experts": 2, + "output_router_logits": false, + "pad_token_id": null, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "rope_theta": 500000, + "rope_type": "default" + }, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "tie_word_embeddings": false, + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 202048 + }, + "tie_word_embeddings": false, + "vision_config": { + "_attn_implementation_autoset": true, + "attention_dropout": 0.0, + "hidden_act": "gelu", + "hidden_size": 1408, + "image_size": 336, + "initializer_range": 0.02, + "intermediate_size": 5632, + "model_type": "llama4_vision_model", + "multi_modal_projector_bias": false, + "norm_eps": 1e-05, + "num_attention_heads": 16, + "num_channels": 3, + "num_hidden_layers": 4, + "patch_size": 14, + "pixel_shuffle_ratio": 0.5, + "projector_dropout": 0.0, + "projector_input_dim": 4096, + "projector_output_dim": 4096, + "rope_parameters": { + "rope_theta": 10000, + "rope_type": "default" + }, + "vision_feature_layer": -1, + "vision_feature_select_strategy": "default", + "vision_output_dim": 4096 + } +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/mixtral/dacorvo/Mixtral-tiny/ce615daa5db83c251d86.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/mixtral/dacorvo/Mixtral-tiny/ce615daa5db83c251d86.json new file mode 100644 index 0000000000000000000000000000000000000000..17f3da19c1ac40695851cdd6287685c9fed86b43 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/mixtral/dacorvo/Mixtral-tiny/ce615daa5db83c251d86.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "dacorvo/Mixtral-tiny", + "_task": "text-generation", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "dtype": "float16", + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3584, + "max_position_embeddings": 1024, + "model_type": "mixtral", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "dacorvo/Mixtral-tiny", + "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "rope_theta": 10000.0, + "rope_type": "default" + }, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 32000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/mobilebert/hf-internal-testing/tiny-random-MobileBertModel/d2923fbdd1af5df4cee7.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/mobilebert/hf-internal-testing/tiny-random-MobileBertModel/d2923fbdd1af5df4cee7.json new file mode 100644 index 0000000000000000000000000000000000000000..cf8dc1c18157ba3a744c6c4a2002a8f0637bb050 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/mobilebert/hf-internal-testing/tiny-random-MobileBertModel/d2923fbdd1af5df4cee7.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MobileBertModel", + "_task": "token-classification", + "architectures": [ + "MobileBertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_activation": true, + "classifier_dropout": null, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 37, + "intra_bottleneck_size": 128, + "key_query_shared_bottleneck": true, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mobilebert", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mobilebert", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "normalization_type": "no_norm", + "num_attention_heads": 4, + "num_feedforward_networks": 4, + "num_hidden_layers": 5, + "trigram_input": true, + "true_hidden_size": 128, + "type_vocab_size": 16, + "use_bottleneck": true, + "use_bottleneck_attention": false, + "vocab_size": 1124 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/mobilevit/hf-internal-testing/tiny-random-mobilevit/497f7d7dac691afa40a2.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/mobilevit/hf-internal-testing/tiny-random-mobilevit/497f7d7dac691afa40a2.json new file mode 100644 index 0000000000000000000000000000000000000000..12a8aea2736f18cbc25ad585944936af7232af08 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/mobilevit/hf-internal-testing/tiny-random-mobilevit/497f7d7dac691afa40a2.json @@ -0,0 +1,2068 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-mobilevit", + "_task": "semantic-segmentation", + "architectures": [ + "MobileViTForImageClassification" + ], + "aspp_dropout_prob": 0.1, + "aspp_out_channels": 256, + "atrous_rates": [ + 6, + 12, + 18 + ], + "attention_probs_dropout_prob": 0.0, + "classifier_dropout_prob": 0.1, + "conv_kernel_size": 3, + "dtype": "float32", + "expand_ratio": 4.0, + "hidden_act": "silu", + "hidden_dropout_prob": 0.1, + "hidden_sizes": [ + 6, + 12, + 24 + ], + "id2label": { + "0": "tench, Tinca tinca", + "1": "goldfish, Carassius auratus", + "2": "great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias", + "3": "tiger shark, Galeocerdo cuvieri", + "4": "hammerhead, hammerhead shark", + "5": "electric ray, crampfish, numbfish, torpedo", + "6": "stingray", + "7": "cock", + "8": "hen", + "9": "ostrich, Struthio camelus", + "10": "brambling, Fringilla montifringilla", + "11": "goldfinch, Carduelis carduelis", + "12": "house finch, linnet, Carpodacus mexicanus", + "13": "junco, snowbird", + "14": "indigo bunting, indigo finch, indigo bird, Passerina cyanea", + "15": "robin, American robin, Turdus migratorius", + "16": "bulbul", + "17": "jay", + "18": "magpie", + "19": "chickadee", + "20": "water ouzel, dipper", + "21": "kite", + "22": "bald eagle, American eagle, Haliaeetus leucocephalus", + "23": "vulture", + "24": "great grey owl, great gray owl, Strix nebulosa", + "25": "European fire salamander, Salamandra salamandra", + "26": "common newt, Triturus vulgaris", + "27": "eft", + "28": "spotted salamander, Ambystoma maculatum", + "29": "axolotl, mud puppy, Ambystoma mexicanum", + "30": "bullfrog, Rana catesbeiana", + "31": "tree frog, tree-frog", + "32": "tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui", + "33": "loggerhead, loggerhead turtle, Caretta caretta", + "34": "leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea", + "35": "mud turtle", + "36": "terrapin", + "37": "box turtle, box tortoise", + "38": "banded gecko", + "39": "common iguana, iguana, Iguana iguana", + "40": "American chameleon, anole, Anolis carolinensis", + "41": "whiptail, whiptail lizard", + "42": "agama", + "43": "frilled lizard, Chlamydosaurus kingi", + "44": "alligator lizard", + "45": "Gila monster, Heloderma suspectum", + "46": "green lizard, Lacerta viridis", + "47": "African chameleon, Chamaeleo chamaeleon", + "48": "Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis", + "49": "African crocodile, Nile crocodile, Crocodylus niloticus", + "50": "American alligator, Alligator mississipiensis", + "51": "triceratops", + "52": "thunder snake, worm snake, Carphophis amoenus", + "53": "ringneck snake, ring-necked snake, ring snake", + "54": "hognose snake, puff adder, sand viper", + "55": "green snake, grass snake", + "56": "king snake, kingsnake", + "57": "garter snake, grass snake", + "58": "water snake", + "59": "vine snake", + "60": "night snake, Hypsiglena torquata", + "61": "boa constrictor, Constrictor constrictor", + "62": "rock python, rock snake, Python sebae", + "63": "Indian cobra, Naja naja", + "64": "green mamba", + "65": "sea snake", + "66": "horned viper, cerastes, sand viper, horned asp, Cerastes cornutus", + "67": "diamondback, diamondback rattlesnake, Crotalus adamanteus", + "68": "sidewinder, horned rattlesnake, Crotalus cerastes", + "69": "trilobite", + "70": "harvestman, daddy longlegs, Phalangium opilio", + "71": "scorpion", + "72": "black and gold garden spider, Argiope aurantia", + "73": "barn spider, Araneus cavaticus", + "74": "garden spider, Aranea diademata", + "75": "black widow, Latrodectus mactans", + "76": "tarantula", + "77": "wolf spider, hunting spider", + "78": "tick", + "79": "centipede", + "80": "black grouse", + "81": "ptarmigan", + "82": "ruffed grouse, partridge, Bonasa umbellus", + "83": "prairie chicken, prairie grouse, prairie fowl", + "84": "peacock", + "85": "quail", + "86": "partridge", + "87": "African grey, African gray, Psittacus erithacus", + "88": "macaw", + "89": "sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita", + "90": "lorikeet", + "91": "coucal", + "92": "bee eater", + "93": "hornbill", + "94": "hummingbird", + "95": "jacamar", + "96": "toucan", + "97": "drake", + "98": "red-breasted merganser, Mergus serrator", + "99": "goose", + "100": "black swan, Cygnus atratus", + "101": "tusker", + "102": "echidna, spiny anteater, anteater", + "103": "platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus", + "104": "wallaby, brush kangaroo", + "105": "koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus", + "106": "wombat", + "107": "jellyfish", + "108": "sea anemone, anemone", + "109": "brain coral", + "110": "flatworm, platyhelminth", + "111": "nematode, nematode worm, roundworm", + "112": "conch", + "113": "snail", + "114": "slug", + "115": "sea slug, nudibranch", + "116": "chiton, coat-of-mail shell, sea cradle, polyplacophore", + "117": "chambered nautilus, pearly nautilus, nautilus", + "118": "Dungeness crab, Cancer magister", + "119": "rock crab, Cancer irroratus", + "120": "fiddler crab", + "121": "king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica", + "122": "American lobster, Northern lobster, Maine lobster, Homarus americanus", + "123": "spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish", + "124": "crayfish, crawfish, crawdad, crawdaddy", + "125": "hermit crab", + "126": "isopod", + "127": "white stork, Ciconia ciconia", + "128": "black stork, Ciconia nigra", + "129": "spoonbill", + "130": "flamingo", + "131": "little blue heron, Egretta caerulea", + "132": "American egret, great white heron, Egretta albus", + "133": "bittern", + "134": "crane", + "135": "limpkin, Aramus pictus", + "136": "European gallinule, Porphyrio porphyrio", + "137": "American coot, marsh hen, mud hen, water hen, Fulica americana", + "138": "bustard", + "139": "ruddy turnstone, Arenaria interpres", + "140": "red-backed sandpiper, dunlin, Erolia alpina", + "141": "redshank, Tringa totanus", + "142": "dowitcher", + "143": "oystercatcher, oyster catcher", + "144": "pelican", + "145": "king penguin, Aptenodytes patagonica", + "146": "albatross, mollymawk", + "147": "grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus", + "148": "killer whale, killer, orca, grampus, sea wolf, Orcinus orca", + "149": "dugong, Dugong dugon", + "150": "sea lion", + "151": "Chihuahua", + "152": "Japanese spaniel", + "153": "Maltese dog, Maltese terrier, Maltese", + "154": "Pekinese, Pekingese, Peke", + "155": "Shih-Tzu", + "156": "Blenheim spaniel", + "157": "papillon", + "158": "toy terrier", + "159": "Rhodesian ridgeback", + "160": "Afghan hound, Afghan", + "161": "basset, basset hound", + "162": "beagle", + "163": "bloodhound, sleuthhound", + "164": "bluetick", + "165": "black-and-tan coonhound", + "166": "Walker hound, Walker foxhound", + "167": "English foxhound", + "168": "redbone", + "169": "borzoi, Russian wolfhound", + "170": "Irish wolfhound", + "171": "Italian greyhound", + "172": "whippet", + "173": "Ibizan hound, Ibizan Podenco", + "174": "Norwegian elkhound, elkhound", + "175": "otterhound, otter hound", + "176": "Saluki, gazelle hound", + "177": "Scottish deerhound, deerhound", + "178": "Weimaraner", + "179": "Staffordshire bullterrier, Staffordshire bull terrier", + "180": "American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier", + "181": "Bedlington terrier", + "182": "Border terrier", + "183": "Kerry blue terrier", + "184": "Irish terrier", + "185": "Norfolk terrier", + "186": "Norwich terrier", + "187": "Yorkshire terrier", + "188": "wire-haired fox terrier", + "189": "Lakeland terrier", + "190": "Sealyham terrier, Sealyham", + "191": "Airedale, Airedale terrier", + "192": "cairn, cairn terrier", + "193": "Australian terrier", + "194": "Dandie Dinmont, Dandie Dinmont terrier", + "195": "Boston bull, Boston terrier", + "196": "miniature schnauzer", + "197": "giant schnauzer", + "198": "standard schnauzer", + "199": "Scotch terrier, Scottish terrier, Scottie", + "200": "Tibetan terrier, chrysanthemum dog", + "201": "silky terrier, Sydney silky", + "202": "soft-coated wheaten terrier", + "203": "West Highland white terrier", + "204": "Lhasa, Lhasa apso", + "205": "flat-coated retriever", + "206": "curly-coated retriever", + "207": "golden retriever", + "208": "Labrador retriever", + "209": "Chesapeake Bay retriever", + "210": "German short-haired pointer", + "211": "vizsla, Hungarian pointer", + "212": "English setter", + "213": "Irish setter, red setter", + "214": "Gordon setter", + "215": "Brittany spaniel", + "216": "clumber, clumber spaniel", + "217": "English springer, English springer spaniel", + "218": "Welsh springer spaniel", + "219": "cocker spaniel, English cocker spaniel, cocker", + "220": "Sussex spaniel", + "221": "Irish water spaniel", + "222": "kuvasz", + "223": "schipperke", + "224": "groenendael", + "225": "malinois", + "226": "briard", + "227": "kelpie", + "228": "komondor", + "229": "Old English sheepdog, bobtail", + "230": "Shetland sheepdog, Shetland sheep dog, Shetland", + "231": "collie", + "232": "Border collie", + "233": "Bouvier des Flandres, Bouviers des Flandres", + "234": "Rottweiler", + "235": "German shepherd, German shepherd dog, German police dog, alsatian", + "236": "Doberman, Doberman pinscher", + "237": "miniature pinscher", + "238": "Greater Swiss Mountain dog", + "239": "Bernese mountain dog", + "240": "Appenzeller", + "241": "EntleBucher", + "242": "boxer", + "243": "bull mastiff", + "244": "Tibetan mastiff", + "245": "French bulldog", + "246": "Great Dane", + "247": "Saint Bernard, St Bernard", + "248": "Eskimo dog, husky", + "249": "malamute, malemute, Alaskan malamute", + "250": "Siberian husky", + "251": "dalmatian, coach dog, carriage dog", + "252": "affenpinscher, monkey pinscher, monkey dog", + "253": "basenji", + "254": "pug, pug-dog", + "255": "Leonberg", + "256": "Newfoundland, Newfoundland dog", + "257": "Great Pyrenees", + "258": "Samoyed, Samoyede", + "259": "Pomeranian", + "260": "chow, chow chow", + "261": "keeshond", + "262": "Brabancon griffon", + "263": "Pembroke, Pembroke Welsh corgi", + "264": "Cardigan, Cardigan Welsh corgi", + "265": "toy poodle", + "266": "miniature poodle", + "267": "standard poodle", + "268": "Mexican hairless", + "269": "timber wolf, grey wolf, gray wolf, Canis lupus", + "270": "white wolf, Arctic wolf, Canis lupus tundrarum", + "271": "red wolf, maned wolf, Canis rufus, Canis niger", + "272": "coyote, prairie wolf, brush wolf, Canis latrans", + "273": "dingo, warrigal, warragal, Canis dingo", + "274": "dhole, Cuon alpinus", + "275": "African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus", + "276": "hyena, hyaena", + "277": "red fox, Vulpes vulpes", + "278": "kit fox, Vulpes macrotis", + "279": "Arctic fox, white fox, Alopex lagopus", + "280": "grey fox, gray fox, Urocyon cinereoargenteus", + "281": "tabby, tabby cat", + "282": "tiger cat", + "283": "Persian cat", + "284": "Siamese cat, Siamese", + "285": "Egyptian cat", + "286": "cougar, puma, catamount, mountain lion, painter, panther, Felis concolor", + "287": "lynx, catamount", + "288": "leopard, Panthera pardus", + "289": "snow leopard, ounce, Panthera uncia", + "290": "jaguar, panther, Panthera onca, Felis onca", + "291": "lion, king of beasts, Panthera leo", + "292": "tiger, Panthera tigris", + "293": "cheetah, chetah, Acinonyx jubatus", + "294": "brown bear, bruin, Ursus arctos", + "295": "American black bear, black bear, Ursus americanus, Euarctos americanus", + "296": "ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus", + "297": "sloth bear, Melursus ursinus, Ursus ursinus", + "298": "mongoose", + "299": "meerkat, mierkat", + "300": "tiger beetle", + "301": "ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle", + "302": "ground beetle, carabid beetle", + "303": "long-horned beetle, longicorn, longicorn beetle", + "304": "leaf beetle, chrysomelid", + "305": "dung beetle", + "306": "rhinoceros beetle", + "307": "weevil", + "308": "fly", + "309": "bee", + "310": "ant, emmet, pismire", + "311": "grasshopper, hopper", + "312": "cricket", + "313": "walking stick, walkingstick, stick insect", + "314": "cockroach, roach", + "315": "mantis, mantid", + "316": "cicada, cicala", + "317": "leafhopper", + "318": "lacewing, lacewing fly", + "319": "dragonfly, darning needle, devil's darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk", + "320": "damselfly", + "321": "admiral", + "322": "ringlet, ringlet butterfly", + "323": "monarch, monarch butterfly, milkweed butterfly, Danaus plexippus", + "324": "cabbage butterfly", + "325": "sulphur butterfly, sulfur butterfly", + "326": "lycaenid, lycaenid butterfly", + "327": "starfish, sea star", + "328": "sea urchin", + "329": "sea cucumber, holothurian", + "330": "wood rabbit, cottontail, cottontail rabbit", + "331": "hare", + "332": "Angora, Angora rabbit", + "333": "hamster", + "334": "porcupine, hedgehog", + "335": "fox squirrel, eastern fox squirrel, Sciurus niger", + "336": "marmot", + "337": "beaver", + "338": "guinea pig, Cavia cobaya", + "339": "sorrel", + "340": "zebra", + "341": "hog, pig, grunter, squealer, Sus scrofa", + "342": "wild boar, boar, Sus scrofa", + "343": "warthog", + "344": "hippopotamus, hippo, river horse, Hippopotamus amphibius", + "345": "ox", + "346": "water buffalo, water ox, Asiatic buffalo, Bubalus bubalis", + "347": "bison", + "348": "ram, tup", + "349": "bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis", + "350": "ibex, Capra ibex", + "351": "hartebeest", + "352": "impala, Aepyceros melampus", + "353": "gazelle", + "354": "Arabian camel, dromedary, Camelus dromedarius", + "355": "llama", + "356": "weasel", + "357": "mink", + "358": "polecat, fitch, foulmart, foumart, Mustela putorius", + "359": "black-footed ferret, ferret, Mustela nigripes", + "360": "otter", + "361": "skunk, polecat, wood pussy", + "362": "badger", + "363": "armadillo", + "364": "three-toed sloth, ai, Bradypus tridactylus", + "365": "orangutan, orang, orangutang, Pongo pygmaeus", + "366": "gorilla, Gorilla gorilla", + "367": "chimpanzee, chimp, Pan troglodytes", + "368": "gibbon, Hylobates lar", + "369": "siamang, Hylobates syndactylus, Symphalangus syndactylus", + "370": "guenon, guenon monkey", + "371": "patas, hussar monkey, Erythrocebus patas", + "372": "baboon", + "373": "macaque", + "374": "langur", + "375": "colobus, colobus monkey", + "376": "proboscis monkey, Nasalis larvatus", + "377": "marmoset", + "378": "capuchin, ringtail, Cebus capucinus", + "379": "howler monkey, howler", + "380": "titi, titi monkey", + "381": "spider monkey, Ateles geoffroyi", + "382": "squirrel monkey, Saimiri sciureus", + "383": "Madagascar cat, ring-tailed lemur, Lemur catta", + "384": "indri, indris, Indri indri, Indri brevicaudatus", + "385": "Indian elephant, Elephas maximus", + "386": "African elephant, Loxodonta africana", + "387": "lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens", + "388": "giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca", + "389": "barracouta, snoek", + "390": "eel", + "391": "coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch", + "392": "rock beauty, Holocanthus tricolor", + "393": "anemone fish", + "394": "sturgeon", + "395": "gar, garfish, garpike, billfish, Lepisosteus osseus", + "396": "lionfish", + "397": "puffer, pufferfish, blowfish, globefish", + "398": "abacus", + "399": "abaya", + "400": "academic gown, academic robe, judge's robe", + "401": "accordion, piano accordion, squeeze box", + "402": "acoustic guitar", + "403": "aircraft carrier, carrier, flattop, attack aircraft carrier", + "404": "airliner", + "405": "airship, dirigible", + "406": "altar", + "407": "ambulance", + "408": "amphibian, amphibious vehicle", + "409": "analog clock", + "410": "apiary, bee house", + "411": "apron", + "412": "ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin", + "413": "assault rifle, assault gun", + "414": "backpack, back pack, knapsack, packsack, rucksack, haversack", + "415": "bakery, bakeshop, bakehouse", + "416": "balance beam, beam", + "417": "balloon", + "418": "ballpoint, ballpoint pen, ballpen, Biro", + "419": "Band Aid", + "420": "banjo", + "421": "bannister, banister, balustrade, balusters, handrail", + "422": "barbell", + "423": "barber chair", + "424": "barbershop", + "425": "barn", + "426": "barometer", + "427": "barrel, cask", + "428": "barrow, garden cart, lawn cart, wheelbarrow", + "429": "baseball", + "430": "basketball", + "431": "bassinet", + "432": "bassoon", + "433": "bathing cap, swimming cap", + "434": "bath towel", + "435": "bathtub, bathing tub, bath, tub", + "436": "beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon", + "437": "beacon, lighthouse, beacon light, pharos", + "438": "beaker", + "439": "bearskin, busby, shako", + "440": "beer bottle", + "441": "beer glass", + "442": "bell cote, bell cot", + "443": "bib", + "444": "bicycle-built-for-two, tandem bicycle, tandem", + "445": "bikini, two-piece", + "446": "binder, ring-binder", + "447": "binoculars, field glasses, opera glasses", + "448": "birdhouse", + "449": "boathouse", + "450": "bobsled, bobsleigh, bob", + "451": "bolo tie, bolo, bola tie, bola", + "452": "bonnet, poke bonnet", + "453": "bookcase", + "454": "bookshop, bookstore, bookstall", + "455": "bottlecap", + "456": "bow", + "457": "bow tie, bow-tie, bowtie", + "458": "brass, memorial tablet, plaque", + "459": "brassiere, bra, bandeau", + "460": "breakwater, groin, groyne, mole, bulwark, seawall, jetty", + "461": "breastplate, aegis, egis", + "462": "broom", + "463": "bucket, pail", + "464": "buckle", + "465": "bulletproof vest", + "466": "bullet train, bullet", + "467": "butcher shop, meat market", + "468": "cab, hack, taxi, taxicab", + "469": "caldron, cauldron", + "470": "candle, taper, wax light", + "471": "cannon", + "472": "canoe", + "473": "can opener, tin opener", + "474": "cardigan", + "475": "car mirror", + "476": "carousel, carrousel, merry-go-round, roundabout, whirligig", + "477": "carpenter's kit, tool kit", + "478": "carton", + "479": "car wheel", + "480": "cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM", + "481": "cassette", + "482": "cassette player", + "483": "castle", + "484": "catamaran", + "485": "CD player", + "486": "cello, violoncello", + "487": "cellular telephone, cellular phone, cellphone, cell, mobile phone", + "488": "chain", + "489": "chainlink fence", + "490": "chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour", + "491": "chain saw, chainsaw", + "492": "chest", + "493": "chiffonier, commode", + "494": "chime, bell, gong", + "495": "china cabinet, china closet", + "496": "Christmas stocking", + "497": "church, church building", + "498": "cinema, movie theater, movie theatre, movie house, picture palace", + "499": "cleaver, meat cleaver, chopper", + "500": "cliff dwelling", + "501": "cloak", + "502": "clog, geta, patten, sabot", + "503": "cocktail shaker", + "504": "coffee mug", + "505": "coffeepot", + "506": "coil, spiral, volute, whorl, helix", + "507": "combination lock", + "508": "computer keyboard, keypad", + "509": "confectionery, confectionary, candy store", + "510": "container ship, containership, container vessel", + "511": "convertible", + "512": "corkscrew, bottle screw", + "513": "cornet, horn, trumpet, trump", + "514": "cowboy boot", + "515": "cowboy hat, ten-gallon hat", + "516": "cradle", + "517": "crane", + "518": "crash helmet", + "519": "crate", + "520": "crib, cot", + "521": "Crock Pot", + "522": "croquet ball", + "523": "crutch", + "524": "cuirass", + "525": "dam, dike, dyke", + "526": "desk", + "527": "desktop computer", + "528": "dial telephone, dial phone", + "529": "diaper, nappy, napkin", + "530": "digital clock", + "531": "digital watch", + "532": "dining table, board", + "533": "dishrag, dishcloth", + "534": "dishwasher, dish washer, dishwashing machine", + "535": "disk brake, disc brake", + "536": "dock, dockage, docking facility", + "537": "dogsled, dog sled, dog sleigh", + "538": "dome", + "539": "doormat, welcome mat", + "540": "drilling platform, offshore rig", + "541": "drum, membranophone, tympan", + "542": "drumstick", + "543": "dumbbell", + "544": "Dutch oven", + "545": "electric fan, blower", + "546": "electric guitar", + "547": "electric locomotive", + "548": "entertainment center", + "549": "envelope", + "550": "espresso maker", + "551": "face powder", + "552": "feather boa, boa", + "553": "file, file cabinet, filing cabinet", + "554": "fireboat", + "555": "fire engine, fire truck", + "556": "fire screen, fireguard", + "557": "flagpole, flagstaff", + "558": "flute, transverse flute", + "559": "folding chair", + "560": "football helmet", + "561": "forklift", + "562": "fountain", + "563": "fountain pen", + "564": "four-poster", + "565": "freight car", + "566": "French horn, horn", + "567": "frying pan, frypan, skillet", + "568": "fur coat", + "569": "garbage truck, dustcart", + "570": "gasmask, respirator, gas helmet", + "571": "gas pump, gasoline pump, petrol pump, island dispenser", + "572": "goblet", + "573": "go-kart", + "574": "golf ball", + "575": "golfcart, golf cart", + "576": "gondola", + "577": "gong, tam-tam", + "578": "gown", + "579": "grand piano, grand", + "580": "greenhouse, nursery, glasshouse", + "581": "grille, radiator grille", + "582": "grocery store, grocery, food market, market", + "583": "guillotine", + "584": "hair slide", + "585": "hair spray", + "586": "half track", + "587": "hammer", + "588": "hamper", + "589": "hand blower, blow dryer, blow drier, hair dryer, hair drier", + "590": "hand-held computer, hand-held microcomputer", + "591": "handkerchief, hankie, hanky, hankey", + "592": "hard disc, hard disk, fixed disk", + "593": "harmonica, mouth organ, harp, mouth harp", + "594": "harp", + "595": "harvester, reaper", + "596": "hatchet", + "597": "holster", + "598": "home theater, home theatre", + "599": "honeycomb", + "600": "hook, claw", + "601": "hoopskirt, crinoline", + "602": "horizontal bar, high bar", + "603": "horse cart, horse-cart", + "604": "hourglass", + "605": "iPod", + "606": "iron, smoothing iron", + "607": "jack-o'-lantern", + "608": "jean, blue jean, denim", + "609": "jeep, landrover", + "610": "jersey, T-shirt, tee shirt", + "611": "jigsaw puzzle", + "612": "jinrikisha, ricksha, rickshaw", + "613": "joystick", + "614": "kimono", + "615": "knee pad", + "616": "knot", + "617": "lab coat, laboratory coat", + "618": "ladle", + "619": "lampshade, lamp shade", + "620": "laptop, laptop computer", + "621": "lawn mower, mower", + "622": "lens cap, lens cover", + "623": "letter opener, paper knife, paperknife", + "624": "library", + "625": "lifeboat", + "626": "lighter, light, igniter, ignitor", + "627": "limousine, limo", + "628": "liner, ocean liner", + "629": "lipstick, lip rouge", + "630": "Loafer", + "631": "lotion", + "632": "loudspeaker, speaker, speaker unit, loudspeaker system, speaker system", + "633": "loupe, jeweler's loupe", + "634": "lumbermill, sawmill", + "635": "magnetic compass", + "636": "mailbag, postbag", + "637": "mailbox, letter box", + "638": "maillot", + "639": "maillot, tank suit", + "640": "manhole cover", + "641": "maraca", + "642": "marimba, xylophone", + "643": "mask", + "644": "matchstick", + "645": "maypole", + "646": "maze, labyrinth", + "647": "measuring cup", + "648": "medicine chest, medicine cabinet", + "649": "megalith, megalithic structure", + "650": "microphone, mike", + "651": "microwave, microwave oven", + "652": "military uniform", + "653": "milk can", + "654": "minibus", + "655": "miniskirt, mini", + "656": "minivan", + "657": "missile", + "658": "mitten", + "659": "mixing bowl", + "660": "mobile home, manufactured home", + "661": "Model T", + "662": "modem", + "663": "monastery", + "664": "monitor", + "665": "moped", + "666": "mortar", + "667": "mortarboard", + "668": "mosque", + "669": "mosquito net", + "670": "motor scooter, scooter", + "671": "mountain bike, all-terrain bike, off-roader", + "672": "mountain tent", + "673": "mouse, computer mouse", + "674": "mousetrap", + "675": "moving van", + "676": "muzzle", + "677": "nail", + "678": "neck brace", + "679": "necklace", + "680": "nipple", + "681": "notebook, notebook computer", + "682": "obelisk", + "683": "oboe, hautboy, hautbois", + "684": "ocarina, sweet potato", + "685": "odometer, hodometer, mileometer, milometer", + "686": "oil filter", + "687": "organ, pipe organ", + "688": "oscilloscope, scope, cathode-ray oscilloscope, CRO", + "689": "overskirt", + "690": "oxcart", + "691": "oxygen mask", + "692": "packet", + "693": "paddle, boat paddle", + "694": "paddlewheel, paddle wheel", + "695": "padlock", + "696": "paintbrush", + "697": "pajama, pyjama, pj's, jammies", + "698": "palace", + "699": "panpipe, pandean pipe, syrinx", + "700": "paper towel", + "701": "parachute, chute", + "702": "parallel bars, bars", + "703": "park bench", + "704": "parking meter", + "705": "passenger car, coach, carriage", + "706": "patio, terrace", + "707": "pay-phone, pay-station", + "708": "pedestal, plinth, footstall", + "709": "pencil box, pencil case", + "710": "pencil sharpener", + "711": "perfume, essence", + "712": "Petri dish", + "713": "photocopier", + "714": "pick, plectrum, plectron", + "715": "pickelhaube", + "716": "picket fence, paling", + "717": "pickup, pickup truck", + "718": "pier", + "719": "piggy bank, penny bank", + "720": "pill bottle", + "721": "pillow", + "722": "ping-pong ball", + "723": "pinwheel", + "724": "pirate, pirate ship", + "725": "pitcher, ewer", + "726": "plane, carpenter's plane, woodworking plane", + "727": "planetarium", + "728": "plastic bag", + "729": "plate rack", + "730": "plow, plough", + "731": "plunger, plumber's helper", + "732": "Polaroid camera, Polaroid Land camera", + "733": "pole", + "734": "police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria", + "735": "poncho", + "736": "pool table, billiard table, snooker table", + "737": "pop bottle, soda bottle", + "738": "pot, flowerpot", + "739": "potter's wheel", + "740": "power drill", + "741": "prayer rug, prayer mat", + "742": "printer", + "743": "prison, prison house", + "744": "projectile, missile", + "745": "projector", + "746": "puck, hockey puck", + "747": "punching bag, punch bag, punching ball, punchball", + "748": "purse", + "749": "quill, quill pen", + "750": "quilt, comforter, comfort, puff", + "751": "racer, race car, racing car", + "752": "racket, racquet", + "753": "radiator", + "754": "radio, wireless", + "755": "radio telescope, radio reflector", + "756": "rain barrel", + "757": "recreational vehicle, RV, R.V.", + "758": "reel", + "759": "reflex camera", + "760": "refrigerator, icebox", + "761": "remote control, remote", + "762": "restaurant, eating house, eating place, eatery", + "763": "revolver, six-gun, six-shooter", + "764": "rifle", + "765": "rocking chair, rocker", + "766": "rotisserie", + "767": "rubber eraser, rubber, pencil eraser", + "768": "rugby ball", + "769": "rule, ruler", + "770": "running shoe", + "771": "safe", + "772": "safety pin", + "773": "saltshaker, salt shaker", + "774": "sandal", + "775": "sarong", + "776": "sax, saxophone", + "777": "scabbard", + "778": "scale, weighing machine", + "779": "school bus", + "780": "schooner", + "781": "scoreboard", + "782": "screen, CRT screen", + "783": "screw", + "784": "screwdriver", + "785": "seat belt, seatbelt", + "786": "sewing machine", + "787": "shield, buckler", + "788": "shoe shop, shoe-shop, shoe store", + "789": "shoji", + "790": "shopping basket", + "791": "shopping cart", + "792": "shovel", + "793": "shower cap", + "794": "shower curtain", + "795": "ski", + "796": "ski mask", + "797": "sleeping bag", + "798": "slide rule, slipstick", + "799": "sliding door", + "800": "slot, one-armed bandit", + "801": "snorkel", + "802": "snowmobile", + "803": "snowplow, snowplough", + "804": "soap dispenser", + "805": "soccer ball", + "806": "sock", + "807": "solar dish, solar collector, solar furnace", + "808": "sombrero", + "809": "soup bowl", + "810": "space bar", + "811": "space heater", + "812": "space shuttle", + "813": "spatula", + "814": "speedboat", + "815": "spider web, spider's web", + "816": "spindle", + "817": "sports car, sport car", + "818": "spotlight, spot", + "819": "stage", + "820": "steam locomotive", + "821": "steel arch bridge", + "822": "steel drum", + "823": "stethoscope", + "824": "stole", + "825": "stone wall", + "826": "stopwatch, stop watch", + "827": "stove", + "828": "strainer", + "829": "streetcar, tram, tramcar, trolley, trolley car", + "830": "stretcher", + "831": "studio couch, day bed", + "832": "stupa, tope", + "833": "submarine, pigboat, sub, U-boat", + "834": "suit, suit of clothes", + "835": "sundial", + "836": "sunglass", + "837": "sunglasses, dark glasses, shades", + "838": "sunscreen, sunblock, sun blocker", + "839": "suspension bridge", + "840": "swab, swob, mop", + "841": "sweatshirt", + "842": "swimming trunks, bathing trunks", + "843": "swing", + "844": "switch, electric switch, electrical switch", + "845": "syringe", + "846": "table lamp", + "847": "tank, army tank, armored combat vehicle, armoured combat vehicle", + "848": "tape player", + "849": "teapot", + "850": "teddy, teddy bear", + "851": "television, television system", + "852": "tennis ball", + "853": "thatch, thatched roof", + "854": "theater curtain, theatre curtain", + "855": "thimble", + "856": "thresher, thrasher, threshing machine", + "857": "throne", + "858": "tile roof", + "859": "toaster", + "860": "tobacco shop, tobacconist shop, tobacconist", + "861": "toilet seat", + "862": "torch", + "863": "totem pole", + "864": "tow truck, tow car, wrecker", + "865": "toyshop", + "866": "tractor", + "867": "trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi", + "868": "tray", + "869": "trench coat", + "870": "tricycle, trike, velocipede", + "871": "trimaran", + "872": "tripod", + "873": "triumphal arch", + "874": "trolleybus, trolley coach, trackless trolley", + "875": "trombone", + "876": "tub, vat", + "877": "turnstile", + "878": "typewriter keyboard", + "879": "umbrella", + "880": "unicycle, monocycle", + "881": "upright, upright piano", + "882": "vacuum, vacuum cleaner", + "883": "vase", + "884": "vault", + "885": "velvet", + "886": "vending machine", + "887": "vestment", + "888": "viaduct", + "889": "violin, fiddle", + "890": "volleyball", + "891": "waffle iron", + "892": "wall clock", + "893": "wallet, billfold, notecase, pocketbook", + "894": "wardrobe, closet, press", + "895": "warplane, military plane", + "896": "washbasin, handbasin, washbowl, lavabo, wash-hand basin", + "897": "washer, automatic washer, washing machine", + "898": "water bottle", + "899": "water jug", + "900": "water tower", + "901": "whiskey jug", + "902": "whistle", + "903": "wig", + "904": "window screen", + "905": "window shade", + "906": "Windsor tie", + "907": "wine bottle", + "908": "wing", + "909": "wok", + "910": "wooden spoon", + "911": "wool, woolen, woollen", + "912": "worm fence, snake fence, snake-rail fence, Virginia fence", + "913": "wreck", + "914": "yawl", + "915": "yurt", + "916": "web site, website, internet site, site", + "917": "comic book", + "918": "crossword puzzle, crossword", + "919": "street sign", + "920": "traffic light, traffic signal, stoplight", + "921": "book jacket, dust cover, dust jacket, dust wrapper", + "922": "menu", + "923": "plate", + "924": "guacamole", + "925": "consomme", + "926": "hot pot, hotpot", + "927": "trifle", + "928": "ice cream, icecream", + "929": "ice lolly, lolly, lollipop, popsicle", + "930": "French loaf", + "931": "bagel, beigel", + "932": "pretzel", + "933": "cheeseburger", + "934": "hotdog, hot dog, red hot", + "935": "mashed potato", + "936": "head cabbage", + "937": "broccoli", + "938": "cauliflower", + "939": "zucchini, courgette", + "940": "spaghetti squash", + "941": "acorn squash", + "942": "butternut squash", + "943": "cucumber, cuke", + "944": "artichoke, globe artichoke", + "945": "bell pepper", + "946": "cardoon", + "947": "mushroom", + "948": "Granny Smith", + "949": "strawberry", + "950": "orange", + "951": "lemon", + "952": "fig", + "953": "pineapple, ananas", + "954": "banana", + "955": "jackfruit, jak, jack", + "956": "custard apple", + "957": "pomegranate", + "958": "hay", + "959": "carbonara", + "960": "chocolate sauce, chocolate syrup", + "961": "dough", + "962": "meat loaf, meatloaf", + "963": "pizza, pizza pie", + "964": "potpie", + "965": "burrito", + "966": "red wine", + "967": "espresso", + "968": "cup", + "969": "eggnog", + "970": "alp", + "971": "bubble", + "972": "cliff, drop, drop-off", + "973": "coral reef", + "974": "geyser", + "975": "lakeside, lakeshore", + "976": "promontory, headland, head, foreland", + "977": "sandbar, sand bar", + "978": "seashore, coast, seacoast, sea-coast", + "979": "valley, vale", + "980": "volcano", + "981": "ballplayer, baseball player", + "982": "groom, bridegroom", + "983": "scuba diver", + "984": "rapeseed", + "985": "daisy", + "986": "yellow lady's slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum", + "987": "corn", + "988": "acorn", + "989": "hip, rose hip, rosehip", + "990": "buckeye, horse chestnut, conker", + "991": "coral fungus", + "992": "agaric", + "993": "gyromitra", + "994": "stinkhorn, carrion fungus", + "995": "earthstar", + "996": "hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa", + "997": "bolete", + "998": "ear, spike, capitulum", + "999": "toilet tissue, toilet paper, bathroom tissue" + }, + "image_size": 256, + "initializer_range": 0.02, + "label2id": { + "Afghan hound, Afghan": 160, + "African chameleon, Chamaeleo chamaeleon": 47, + "African crocodile, Nile crocodile, Crocodylus niloticus": 49, + "African elephant, Loxodonta africana": 386, + "African grey, African gray, Psittacus erithacus": 87, + "African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus": 275, + "Airedale, Airedale terrier": 191, + "American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier": 180, + "American alligator, Alligator mississipiensis": 50, + "American black bear, black bear, Ursus americanus, Euarctos americanus": 295, + "American chameleon, anole, Anolis carolinensis": 40, + "American coot, marsh hen, mud hen, water hen, Fulica americana": 137, + "American egret, great white heron, Egretta albus": 132, + "American lobster, Northern lobster, Maine lobster, Homarus americanus": 122, + "Angora, Angora rabbit": 332, + "Appenzeller": 240, + "Arabian camel, dromedary, Camelus dromedarius": 354, + "Arctic fox, white fox, Alopex lagopus": 279, + "Australian terrier": 193, + "Band Aid": 419, + "Bedlington terrier": 181, + "Bernese mountain dog": 239, + "Blenheim spaniel": 156, + "Border collie": 232, + "Border terrier": 182, + "Boston bull, Boston terrier": 195, + "Bouvier des Flandres, Bouviers des Flandres": 233, + "Brabancon griffon": 262, + "Brittany spaniel": 215, + "CD player": 485, + "Cardigan, Cardigan Welsh corgi": 264, + "Chesapeake Bay retriever": 209, + "Chihuahua": 151, + "Christmas stocking": 496, + "Crock Pot": 521, + "Dandie Dinmont, Dandie Dinmont terrier": 194, + "Doberman, Doberman pinscher": 236, + "Dungeness crab, Cancer magister": 118, + "Dutch oven": 544, + "Egyptian cat": 285, + "English foxhound": 167, + "English setter": 212, + "English springer, English springer spaniel": 217, + "EntleBucher": 241, + "Eskimo dog, husky": 248, + "European fire salamander, Salamandra salamandra": 25, + "European gallinule, Porphyrio porphyrio": 136, + "French bulldog": 245, + "French horn, horn": 566, + "French loaf": 930, + "German shepherd, German shepherd dog, German police dog, alsatian": 235, + "German short-haired pointer": 210, + "Gila monster, Heloderma suspectum": 45, + "Gordon setter": 214, + "Granny Smith": 948, + "Great Dane": 246, + "Great Pyrenees": 257, + "Greater Swiss Mountain dog": 238, + "Ibizan hound, Ibizan Podenco": 173, + "Indian cobra, Naja naja": 63, + "Indian elephant, Elephas maximus": 385, + "Irish setter, red setter": 213, + "Irish terrier": 184, + "Irish water spaniel": 221, + "Irish wolfhound": 170, + "Italian greyhound": 171, + "Japanese spaniel": 152, + "Kerry blue terrier": 183, + "Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis": 48, + "Labrador retriever": 208, + "Lakeland terrier": 189, + "Leonberg": 255, + "Lhasa, Lhasa apso": 204, + "Loafer": 630, + "Madagascar cat, ring-tailed lemur, Lemur catta": 383, + "Maltese dog, Maltese terrier, Maltese": 153, + "Mexican hairless": 268, + "Model T": 661, + "Newfoundland, Newfoundland dog": 256, + "Norfolk terrier": 185, + "Norwegian elkhound, elkhound": 174, + "Norwich terrier": 186, + "Old English sheepdog, bobtail": 229, + "Pekinese, Pekingese, Peke": 154, + "Pembroke, Pembroke Welsh corgi": 263, + "Persian cat": 283, + "Petri dish": 712, + "Polaroid camera, Polaroid Land camera": 732, + "Pomeranian": 259, + "Rhodesian ridgeback": 159, + "Rottweiler": 234, + "Saint Bernard, St Bernard": 247, + "Saluki, gazelle hound": 176, + "Samoyed, Samoyede": 258, + "Scotch terrier, Scottish terrier, Scottie": 199, + "Scottish deerhound, deerhound": 177, + "Sealyham terrier, Sealyham": 190, + "Shetland sheepdog, Shetland sheep dog, Shetland": 230, + "Shih-Tzu": 155, + "Siamese cat, Siamese": 284, + "Siberian husky": 250, + "Staffordshire bullterrier, Staffordshire bull terrier": 179, + "Sussex spaniel": 220, + "Tibetan mastiff": 244, + "Tibetan terrier, chrysanthemum dog": 200, + "Walker hound, Walker foxhound": 166, + "Weimaraner": 178, + "Welsh springer spaniel": 218, + "West Highland white terrier": 203, + "Windsor tie": 906, + "Yorkshire terrier": 187, + "abacus": 398, + "abaya": 399, + "academic gown, academic robe, judge's robe": 400, + "accordion, piano accordion, squeeze box": 401, + "acorn": 988, + "acorn squash": 941, + "acoustic guitar": 402, + "admiral": 321, + "affenpinscher, monkey pinscher, monkey dog": 252, + "agama": 42, + "agaric": 992, + "aircraft carrier, carrier, flattop, attack aircraft carrier": 403, + "airliner": 404, + "airship, dirigible": 405, + "albatross, mollymawk": 146, + "alligator lizard": 44, + "alp": 970, + "altar": 406, + "ambulance": 407, + "amphibian, amphibious vehicle": 408, + "analog clock": 409, + "anemone fish": 393, + "ant, emmet, pismire": 310, + "apiary, bee house": 410, + "apron": 411, + "armadillo": 363, + "artichoke, globe artichoke": 944, + "ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin": 412, + "assault rifle, assault gun": 413, + "axolotl, mud puppy, Ambystoma mexicanum": 29, + "baboon": 372, + "backpack, back pack, knapsack, packsack, rucksack, haversack": 414, + "badger": 362, + "bagel, beigel": 931, + "bakery, bakeshop, bakehouse": 415, + "balance beam, beam": 416, + "bald eagle, American eagle, Haliaeetus leucocephalus": 22, + "balloon": 417, + "ballplayer, baseball player": 981, + "ballpoint, ballpoint pen, ballpen, Biro": 418, + "banana": 954, + "banded gecko": 38, + "banjo": 420, + "bannister, banister, balustrade, balusters, handrail": 421, + "barbell": 422, + "barber chair": 423, + "barbershop": 424, + "barn": 425, + "barn spider, Araneus cavaticus": 73, + "barometer": 426, + "barracouta, snoek": 389, + "barrel, cask": 427, + "barrow, garden cart, lawn cart, wheelbarrow": 428, + "baseball": 429, + "basenji": 253, + "basketball": 430, + "basset, basset hound": 161, + "bassinet": 431, + "bassoon": 432, + "bath towel": 434, + "bathing cap, swimming cap": 433, + "bathtub, bathing tub, bath, tub": 435, + "beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon": 436, + "beacon, lighthouse, beacon light, pharos": 437, + "beagle": 162, + "beaker": 438, + "bearskin, busby, shako": 439, + "beaver": 337, + "bee": 309, + "bee eater": 92, + "beer bottle": 440, + "beer glass": 441, + "bell cote, bell cot": 442, + "bell pepper": 945, + "bib": 443, + "bicycle-built-for-two, tandem bicycle, tandem": 444, + "bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis": 349, + "bikini, two-piece": 445, + "binder, ring-binder": 446, + "binoculars, field glasses, opera glasses": 447, + "birdhouse": 448, + "bison": 347, + "bittern": 133, + "black and gold garden spider, Argiope aurantia": 72, + "black grouse": 80, + "black stork, Ciconia nigra": 128, + "black swan, Cygnus atratus": 100, + "black widow, Latrodectus mactans": 75, + "black-and-tan coonhound": 165, + "black-footed ferret, ferret, Mustela nigripes": 359, + "bloodhound, sleuthhound": 163, + "bluetick": 164, + "boa constrictor, Constrictor constrictor": 61, + "boathouse": 449, + "bobsled, bobsleigh, bob": 450, + "bolete": 997, + "bolo tie, bolo, bola tie, bola": 451, + "bonnet, poke bonnet": 452, + "book jacket, dust cover, dust jacket, dust wrapper": 921, + "bookcase": 453, + "bookshop, bookstore, bookstall": 454, + "borzoi, Russian wolfhound": 169, + "bottlecap": 455, + "bow": 456, + "bow tie, bow-tie, bowtie": 457, + "box turtle, box tortoise": 37, + "boxer": 242, + "brain coral": 109, + "brambling, Fringilla montifringilla": 10, + "brass, memorial tablet, plaque": 458, + "brassiere, bra, bandeau": 459, + "breakwater, groin, groyne, mole, bulwark, seawall, jetty": 460, + "breastplate, aegis, egis": 461, + "briard": 226, + "broccoli": 937, + "broom": 462, + "brown bear, bruin, Ursus arctos": 294, + "bubble": 971, + "bucket, pail": 463, + "buckeye, horse chestnut, conker": 990, + "buckle": 464, + "bulbul": 16, + "bull mastiff": 243, + "bullet train, bullet": 466, + "bulletproof vest": 465, + "bullfrog, Rana catesbeiana": 30, + "burrito": 965, + "bustard": 138, + "butcher shop, meat market": 467, + "butternut squash": 942, + "cab, hack, taxi, taxicab": 468, + "cabbage butterfly": 324, + "cairn, cairn terrier": 192, + "caldron, cauldron": 469, + "can opener, tin opener": 473, + "candle, taper, wax light": 470, + "cannon": 471, + "canoe": 472, + "capuchin, ringtail, Cebus capucinus": 378, + "car mirror": 475, + "car wheel": 479, + "carbonara": 959, + "cardigan": 474, + "cardoon": 946, + "carousel, carrousel, merry-go-round, roundabout, whirligig": 476, + "carpenter's kit, tool kit": 477, + "carton": 478, + "cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM": 480, + "cassette": 481, + "cassette player": 482, + "castle": 483, + "catamaran": 484, + "cauliflower": 938, + "cello, violoncello": 486, + "cellular telephone, cellular phone, cellphone, cell, mobile phone": 487, + "centipede": 79, + "chain": 488, + "chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour": 490, + "chain saw, chainsaw": 491, + "chainlink fence": 489, + "chambered nautilus, pearly nautilus, nautilus": 117, + "cheeseburger": 933, + "cheetah, chetah, Acinonyx jubatus": 293, + "chest": 492, + "chickadee": 19, + "chiffonier, commode": 493, + "chime, bell, gong": 494, + "chimpanzee, chimp, Pan troglodytes": 367, + "china cabinet, china closet": 495, + "chiton, coat-of-mail shell, sea cradle, polyplacophore": 116, + "chocolate sauce, chocolate syrup": 960, + "chow, chow chow": 260, + "church, church building": 497, + "cicada, cicala": 316, + "cinema, movie theater, movie theatre, movie house, picture palace": 498, + "cleaver, meat cleaver, chopper": 499, + "cliff dwelling": 500, + "cliff, drop, drop-off": 972, + "cloak": 501, + "clog, geta, patten, sabot": 502, + "clumber, clumber spaniel": 216, + "cock": 7, + "cocker spaniel, English cocker spaniel, cocker": 219, + "cockroach, roach": 314, + "cocktail shaker": 503, + "coffee mug": 504, + "coffeepot": 505, + "coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch": 391, + "coil, spiral, volute, whorl, helix": 506, + "collie": 231, + "colobus, colobus monkey": 375, + "combination lock": 507, + "comic book": 917, + "common iguana, iguana, Iguana iguana": 39, + "common newt, Triturus vulgaris": 26, + "computer keyboard, keypad": 508, + "conch": 112, + "confectionery, confectionary, candy store": 509, + "consomme": 925, + "container ship, containership, container vessel": 510, + "convertible": 511, + "coral fungus": 991, + "coral reef": 973, + "corkscrew, bottle screw": 512, + "corn": 987, + "cornet, horn, trumpet, trump": 513, + "coucal": 91, + "cougar, puma, catamount, mountain lion, painter, panther, Felis concolor": 286, + "cowboy boot": 514, + "cowboy hat, ten-gallon hat": 515, + "coyote, prairie wolf, brush wolf, Canis latrans": 272, + "cradle": 516, + "crane": 517, + "crash helmet": 518, + "crate": 519, + "crayfish, crawfish, crawdad, crawdaddy": 124, + "crib, cot": 520, + "cricket": 312, + "croquet ball": 522, + "crossword puzzle, crossword": 918, + "crutch": 523, + "cucumber, cuke": 943, + "cuirass": 524, + "cup": 968, + "curly-coated retriever": 206, + "custard apple": 956, + "daisy": 985, + "dalmatian, coach dog, carriage dog": 251, + "dam, dike, dyke": 525, + "damselfly": 320, + "desk": 526, + "desktop computer": 527, + "dhole, Cuon alpinus": 274, + "dial telephone, dial phone": 528, + "diamondback, diamondback rattlesnake, Crotalus adamanteus": 67, + "diaper, nappy, napkin": 529, + "digital clock": 530, + "digital watch": 531, + "dingo, warrigal, warragal, Canis dingo": 273, + "dining table, board": 532, + "dishrag, dishcloth": 533, + "dishwasher, dish washer, dishwashing machine": 534, + "disk brake, disc brake": 535, + "dock, dockage, docking facility": 536, + "dogsled, dog sled, dog sleigh": 537, + "dome": 538, + "doormat, welcome mat": 539, + "dough": 961, + "dowitcher": 142, + "dragonfly, darning needle, devil's darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk": 319, + "drake": 97, + "drilling platform, offshore rig": 540, + "drum, membranophone, tympan": 541, + "drumstick": 542, + "dugong, Dugong dugon": 149, + "dumbbell": 543, + "dung beetle": 305, + "ear, spike, capitulum": 998, + "earthstar": 995, + "echidna, spiny anteater, anteater": 102, + "eel": 390, + "eft": 27, + "eggnog": 969, + "electric fan, blower": 545, + "electric guitar": 546, + "electric locomotive": 547, + "electric ray, crampfish, numbfish, torpedo": 5, + "entertainment center": 548, + "envelope": 549, + "espresso": 967, + "espresso maker": 550, + "face powder": 551, + "feather boa, boa": 552, + "fiddler crab": 120, + "fig": 952, + "file, file cabinet, filing cabinet": 553, + "fire engine, fire truck": 555, + "fire screen, fireguard": 556, + "fireboat": 554, + "flagpole, flagstaff": 557, + "flamingo": 130, + "flat-coated retriever": 205, + "flatworm, platyhelminth": 110, + "flute, transverse flute": 558, + "fly": 308, + "folding chair": 559, + "football helmet": 560, + "forklift": 561, + "fountain": 562, + "fountain pen": 563, + "four-poster": 564, + "fox squirrel, eastern fox squirrel, Sciurus niger": 335, + "freight car": 565, + "frilled lizard, Chlamydosaurus kingi": 43, + "frying pan, frypan, skillet": 567, + "fur coat": 568, + "gar, garfish, garpike, billfish, Lepisosteus osseus": 395, + "garbage truck, dustcart": 569, + "garden spider, Aranea diademata": 74, + "garter snake, grass snake": 57, + "gas pump, gasoline pump, petrol pump, island dispenser": 571, + "gasmask, respirator, gas helmet": 570, + "gazelle": 353, + "geyser": 974, + "giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca": 388, + "giant schnauzer": 197, + "gibbon, Hylobates lar": 368, + "go-kart": 573, + "goblet": 572, + "golden retriever": 207, + "goldfinch, Carduelis carduelis": 11, + "goldfish, Carassius auratus": 1, + "golf ball": 574, + "golfcart, golf cart": 575, + "gondola": 576, + "gong, tam-tam": 577, + "goose": 99, + "gorilla, Gorilla gorilla": 366, + "gown": 578, + "grand piano, grand": 579, + "grasshopper, hopper": 311, + "great grey owl, great gray owl, Strix nebulosa": 24, + "great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias": 2, + "green lizard, Lacerta viridis": 46, + "green mamba": 64, + "green snake, grass snake": 55, + "greenhouse, nursery, glasshouse": 580, + "grey fox, gray fox, Urocyon cinereoargenteus": 280, + "grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus": 147, + "grille, radiator grille": 581, + "grocery store, grocery, food market, market": 582, + "groenendael": 224, + "groom, bridegroom": 982, + "ground beetle, carabid beetle": 302, + "guacamole": 924, + "guenon, guenon monkey": 370, + "guillotine": 583, + "guinea pig, Cavia cobaya": 338, + "gyromitra": 993, + "hair slide": 584, + "hair spray": 585, + "half track": 586, + "hammer": 587, + "hammerhead, hammerhead shark": 4, + "hamper": 588, + "hamster": 333, + "hand blower, blow dryer, blow drier, hair dryer, hair drier": 589, + "hand-held computer, hand-held microcomputer": 590, + "handkerchief, hankie, hanky, hankey": 591, + "hard disc, hard disk, fixed disk": 592, + "hare": 331, + "harmonica, mouth organ, harp, mouth harp": 593, + "harp": 594, + "hartebeest": 351, + "harvester, reaper": 595, + "harvestman, daddy longlegs, Phalangium opilio": 70, + "hatchet": 596, + "hay": 958, + "head cabbage": 936, + "hen": 8, + "hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa": 996, + "hermit crab": 125, + "hip, rose hip, rosehip": 989, + "hippopotamus, hippo, river horse, Hippopotamus amphibius": 344, + "hog, pig, grunter, squealer, Sus scrofa": 341, + "hognose snake, puff adder, sand viper": 54, + "holster": 597, + "home theater, home theatre": 598, + "honeycomb": 599, + "hook, claw": 600, + "hoopskirt, crinoline": 601, + "horizontal bar, high bar": 602, + "hornbill": 93, + "horned viper, cerastes, sand viper, horned asp, Cerastes cornutus": 66, + "horse cart, horse-cart": 603, + "hot pot, hotpot": 926, + "hotdog, hot dog, red hot": 934, + "hourglass": 604, + "house finch, linnet, Carpodacus mexicanus": 12, + "howler monkey, howler": 379, + "hummingbird": 94, + "hyena, hyaena": 276, + "iPod": 605, + "ibex, Capra ibex": 350, + "ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus": 296, + "ice cream, icecream": 928, + "ice lolly, lolly, lollipop, popsicle": 929, + "impala, Aepyceros melampus": 352, + "indigo bunting, indigo finch, indigo bird, Passerina cyanea": 14, + "indri, indris, Indri indri, Indri brevicaudatus": 384, + "iron, smoothing iron": 606, + "isopod": 126, + "jacamar": 95, + "jack-o'-lantern": 607, + "jackfruit, jak, jack": 955, + "jaguar, panther, Panthera onca, Felis onca": 290, + "jay": 17, + "jean, blue jean, denim": 608, + "jeep, landrover": 609, + "jellyfish": 107, + "jersey, T-shirt, tee shirt": 610, + "jigsaw puzzle": 611, + "jinrikisha, ricksha, rickshaw": 612, + "joystick": 613, + "junco, snowbird": 13, + "keeshond": 261, + "kelpie": 227, + "killer whale, killer, orca, grampus, sea wolf, Orcinus orca": 148, + "kimono": 614, + "king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica": 121, + "king penguin, Aptenodytes patagonica": 145, + "king snake, kingsnake": 56, + "kit fox, Vulpes macrotis": 278, + "kite": 21, + "knee pad": 615, + "knot": 616, + "koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus": 105, + "komondor": 228, + "kuvasz": 222, + "lab coat, laboratory coat": 617, + "lacewing, lacewing fly": 318, + "ladle": 618, + "ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle": 301, + "lakeside, lakeshore": 975, + "lampshade, lamp shade": 619, + "langur": 374, + "laptop, laptop computer": 620, + "lawn mower, mower": 621, + "leaf beetle, chrysomelid": 304, + "leafhopper": 317, + "leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea": 34, + "lemon": 951, + "lens cap, lens cover": 622, + "leopard, Panthera pardus": 288, + "lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens": 387, + "letter opener, paper knife, paperknife": 623, + "library": 624, + "lifeboat": 625, + "lighter, light, igniter, ignitor": 626, + "limousine, limo": 627, + "limpkin, Aramus pictus": 135, + "liner, ocean liner": 628, + "lion, king of beasts, Panthera leo": 291, + "lionfish": 396, + "lipstick, lip rouge": 629, + "little blue heron, Egretta caerulea": 131, + "llama": 355, + "loggerhead, loggerhead turtle, Caretta caretta": 33, + "long-horned beetle, longicorn, longicorn beetle": 303, + "lorikeet": 90, + "lotion": 631, + "loudspeaker, speaker, speaker unit, loudspeaker system, speaker system": 632, + "loupe, jeweler's loupe": 633, + "lumbermill, sawmill": 634, + "lycaenid, lycaenid butterfly": 326, + "lynx, catamount": 287, + "macaque": 373, + "macaw": 88, + "magnetic compass": 635, + "magpie": 18, + "mailbag, postbag": 636, + "mailbox, letter box": 637, + "maillot": 638, + "maillot, tank suit": 639, + "malamute, malemute, Alaskan malamute": 249, + "malinois": 225, + "manhole cover": 640, + "mantis, mantid": 315, + "maraca": 641, + "marimba, xylophone": 642, + "marmoset": 377, + "marmot": 336, + "mashed potato": 935, + "mask": 643, + "matchstick": 644, + "maypole": 645, + "maze, labyrinth": 646, + "measuring cup": 647, + "meat loaf, meatloaf": 962, + "medicine chest, medicine cabinet": 648, + "meerkat, mierkat": 299, + "megalith, megalithic structure": 649, + "menu": 922, + "microphone, mike": 650, + "microwave, microwave oven": 651, + "military uniform": 652, + "milk can": 653, + "miniature pinscher": 237, + "miniature poodle": 266, + "miniature schnauzer": 196, + "minibus": 654, + "miniskirt, mini": 655, + "minivan": 656, + "mink": 357, + "missile": 657, + "mitten": 658, + "mixing bowl": 659, + "mobile home, manufactured home": 660, + "modem": 662, + "monarch, monarch butterfly, milkweed butterfly, Danaus plexippus": 323, + "monastery": 663, + "mongoose": 298, + "monitor": 664, + "moped": 665, + "mortar": 666, + "mortarboard": 667, + "mosque": 668, + "mosquito net": 669, + "motor scooter, scooter": 670, + "mountain bike, all-terrain bike, off-roader": 671, + "mountain tent": 672, + "mouse, computer mouse": 673, + "mousetrap": 674, + "moving van": 675, + "mud turtle": 35, + "mushroom": 947, + "muzzle": 676, + "nail": 677, + "neck brace": 678, + "necklace": 679, + "nematode, nematode worm, roundworm": 111, + "night snake, Hypsiglena torquata": 60, + "nipple": 680, + "notebook, notebook computer": 681, + "obelisk": 682, + "oboe, hautboy, hautbois": 683, + "ocarina, sweet potato": 684, + "odometer, hodometer, mileometer, milometer": 685, + "oil filter": 686, + "orange": 950, + "orangutan, orang, orangutang, Pongo pygmaeus": 365, + "organ, pipe organ": 687, + "oscilloscope, scope, cathode-ray oscilloscope, CRO": 688, + "ostrich, Struthio camelus": 9, + "otter": 360, + "otterhound, otter hound": 175, + "overskirt": 689, + "ox": 345, + "oxcart": 690, + "oxygen mask": 691, + "oystercatcher, oyster catcher": 143, + "packet": 692, + "paddle, boat paddle": 693, + "paddlewheel, paddle wheel": 694, + "padlock": 695, + "paintbrush": 696, + "pajama, pyjama, pj's, jammies": 697, + "palace": 698, + "panpipe, pandean pipe, syrinx": 699, + "paper towel": 700, + "papillon": 157, + "parachute, chute": 701, + "parallel bars, bars": 702, + "park bench": 703, + "parking meter": 704, + "partridge": 86, + "passenger car, coach, carriage": 705, + "patas, hussar monkey, Erythrocebus patas": 371, + "patio, terrace": 706, + "pay-phone, pay-station": 707, + "peacock": 84, + "pedestal, plinth, footstall": 708, + "pelican": 144, + "pencil box, pencil case": 709, + "pencil sharpener": 710, + "perfume, essence": 711, + "photocopier": 713, + "pick, plectrum, plectron": 714, + "pickelhaube": 715, + "picket fence, paling": 716, + "pickup, pickup truck": 717, + "pier": 718, + "piggy bank, penny bank": 719, + "pill bottle": 720, + "pillow": 721, + "pineapple, ananas": 953, + "ping-pong ball": 722, + "pinwheel": 723, + "pirate, pirate ship": 724, + "pitcher, ewer": 725, + "pizza, pizza pie": 963, + "plane, carpenter's plane, woodworking plane": 726, + "planetarium": 727, + "plastic bag": 728, + "plate": 923, + "plate rack": 729, + "platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus": 103, + "plow, plough": 730, + "plunger, plumber's helper": 731, + "pole": 733, + "polecat, fitch, foulmart, foumart, Mustela putorius": 358, + "police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria": 734, + "pomegranate": 957, + "poncho": 735, + "pool table, billiard table, snooker table": 736, + "pop bottle, soda bottle": 737, + "porcupine, hedgehog": 334, + "pot, flowerpot": 738, + "potpie": 964, + "potter's wheel": 739, + "power drill": 740, + "prairie chicken, prairie grouse, prairie fowl": 83, + "prayer rug, prayer mat": 741, + "pretzel": 932, + "printer": 742, + "prison, prison house": 743, + "proboscis monkey, Nasalis larvatus": 376, + "projectile, missile": 744, + "projector": 745, + "promontory, headland, head, foreland": 976, + "ptarmigan": 81, + "puck, hockey puck": 746, + "puffer, pufferfish, blowfish, globefish": 397, + "pug, pug-dog": 254, + "punching bag, punch bag, punching ball, punchball": 747, + "purse": 748, + "quail": 85, + "quill, quill pen": 749, + "quilt, comforter, comfort, puff": 750, + "racer, race car, racing car": 751, + "racket, racquet": 752, + "radiator": 753, + "radio telescope, radio reflector": 755, + "radio, wireless": 754, + "rain barrel": 756, + "ram, tup": 348, + "rapeseed": 984, + "recreational vehicle, RV, R.V.": 757, + "red fox, Vulpes vulpes": 277, + "red wine": 966, + "red wolf, maned wolf, Canis rufus, Canis niger": 271, + "red-backed sandpiper, dunlin, Erolia alpina": 140, + "red-breasted merganser, Mergus serrator": 98, + "redbone": 168, + "redshank, Tringa totanus": 141, + "reel": 758, + "reflex camera": 759, + "refrigerator, icebox": 760, + "remote control, remote": 761, + "restaurant, eating house, eating place, eatery": 762, + "revolver, six-gun, six-shooter": 763, + "rhinoceros beetle": 306, + "rifle": 764, + "ringlet, ringlet butterfly": 322, + "ringneck snake, ring-necked snake, ring snake": 53, + "robin, American robin, Turdus migratorius": 15, + "rock beauty, Holocanthus tricolor": 392, + "rock crab, Cancer irroratus": 119, + "rock python, rock snake, Python sebae": 62, + "rocking chair, rocker": 765, + "rotisserie": 766, + "rubber eraser, rubber, pencil eraser": 767, + "ruddy turnstone, Arenaria interpres": 139, + "ruffed grouse, partridge, Bonasa umbellus": 82, + "rugby ball": 768, + "rule, ruler": 769, + "running shoe": 770, + "safe": 771, + "safety pin": 772, + "saltshaker, salt shaker": 773, + "sandal": 774, + "sandbar, sand bar": 977, + "sarong": 775, + "sax, saxophone": 776, + "scabbard": 777, + "scale, weighing machine": 778, + "schipperke": 223, + "school bus": 779, + "schooner": 780, + "scoreboard": 781, + "scorpion": 71, + "screen, CRT screen": 782, + "screw": 783, + "screwdriver": 784, + "scuba diver": 983, + "sea anemone, anemone": 108, + "sea cucumber, holothurian": 329, + "sea lion": 150, + "sea slug, nudibranch": 115, + "sea snake": 65, + "sea urchin": 328, + "seashore, coast, seacoast, sea-coast": 978, + "seat belt, seatbelt": 785, + "sewing machine": 786, + "shield, buckler": 787, + "shoe shop, shoe-shop, shoe store": 788, + "shoji": 789, + "shopping basket": 790, + "shopping cart": 791, + "shovel": 792, + "shower cap": 793, + "shower curtain": 794, + "siamang, Hylobates syndactylus, Symphalangus syndactylus": 369, + "sidewinder, horned rattlesnake, Crotalus cerastes": 68, + "silky terrier, Sydney silky": 201, + "ski": 795, + "ski mask": 796, + "skunk, polecat, wood pussy": 361, + "sleeping bag": 797, + "slide rule, slipstick": 798, + "sliding door": 799, + "slot, one-armed bandit": 800, + "sloth bear, Melursus ursinus, Ursus ursinus": 297, + "slug": 114, + "snail": 113, + "snorkel": 801, + "snow leopard, ounce, Panthera uncia": 289, + "snowmobile": 802, + "snowplow, snowplough": 803, + "soap dispenser": 804, + "soccer ball": 805, + "sock": 806, + "soft-coated wheaten terrier": 202, + "solar dish, solar collector, solar furnace": 807, + "sombrero": 808, + "sorrel": 339, + "soup bowl": 809, + "space bar": 810, + "space heater": 811, + "space shuttle": 812, + "spaghetti squash": 940, + "spatula": 813, + "speedboat": 814, + "spider monkey, Ateles geoffroyi": 381, + "spider web, spider's web": 815, + "spindle": 816, + "spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish": 123, + "spoonbill": 129, + "sports car, sport car": 817, + "spotlight, spot": 818, + "spotted salamander, Ambystoma maculatum": 28, + "squirrel monkey, Saimiri sciureus": 382, + "stage": 819, + "standard poodle": 267, + "standard schnauzer": 198, + "starfish, sea star": 327, + "steam locomotive": 820, + "steel arch bridge": 821, + "steel drum": 822, + "stethoscope": 823, + "stingray": 6, + "stinkhorn, carrion fungus": 994, + "stole": 824, + "stone wall": 825, + "stopwatch, stop watch": 826, + "stove": 827, + "strainer": 828, + "strawberry": 949, + "street sign": 919, + "streetcar, tram, tramcar, trolley, trolley car": 829, + "stretcher": 830, + "studio couch, day bed": 831, + "stupa, tope": 832, + "sturgeon": 394, + "submarine, pigboat, sub, U-boat": 833, + "suit, suit of clothes": 834, + "sulphur butterfly, sulfur butterfly": 325, + "sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita": 89, + "sundial": 835, + "sunglass": 836, + "sunglasses, dark glasses, shades": 837, + "sunscreen, sunblock, sun blocker": 838, + "suspension bridge": 839, + "swab, swob, mop": 840, + "sweatshirt": 841, + "swimming trunks, bathing trunks": 842, + "swing": 843, + "switch, electric switch, electrical switch": 844, + "syringe": 845, + "tabby, tabby cat": 281, + "table lamp": 846, + "tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui": 32, + "tank, army tank, armored combat vehicle, armoured combat vehicle": 847, + "tape player": 848, + "tarantula": 76, + "teapot": 849, + "teddy, teddy bear": 850, + "television, television system": 851, + "tench, Tinca tinca": 0, + "tennis ball": 852, + "terrapin": 36, + "thatch, thatched roof": 853, + "theater curtain, theatre curtain": 854, + "thimble": 855, + "three-toed sloth, ai, Bradypus tridactylus": 364, + "thresher, thrasher, threshing machine": 856, + "throne": 857, + "thunder snake, worm snake, Carphophis amoenus": 52, + "tick": 78, + "tiger beetle": 300, + "tiger cat": 282, + "tiger shark, Galeocerdo cuvieri": 3, + "tiger, Panthera tigris": 292, + "tile roof": 858, + "timber wolf, grey wolf, gray wolf, Canis lupus": 269, + "titi, titi monkey": 380, + "toaster": 859, + "tobacco shop, tobacconist shop, tobacconist": 860, + "toilet seat": 861, + "toilet tissue, toilet paper, bathroom tissue": 999, + "torch": 862, + "totem pole": 863, + "toucan": 96, + "tow truck, tow car, wrecker": 864, + "toy poodle": 265, + "toy terrier": 158, + "toyshop": 865, + "tractor": 866, + "traffic light, traffic signal, stoplight": 920, + "trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi": 867, + "tray": 868, + "tree frog, tree-frog": 31, + "trench coat": 869, + "triceratops": 51, + "tricycle, trike, velocipede": 870, + "trifle": 927, + "trilobite": 69, + "trimaran": 871, + "tripod": 872, + "triumphal arch": 873, + "trolleybus, trolley coach, trackless trolley": 874, + "trombone": 875, + "tub, vat": 876, + "turnstile": 877, + "tusker": 101, + "typewriter keyboard": 878, + "umbrella": 879, + "unicycle, monocycle": 880, + "upright, upright piano": 881, + "vacuum, vacuum cleaner": 882, + "valley, vale": 979, + "vase": 883, + "vault": 884, + "velvet": 885, + "vending machine": 886, + "vestment": 887, + "viaduct": 888, + "vine snake": 59, + "violin, fiddle": 889, + "vizsla, Hungarian pointer": 211, + "volcano": 980, + "volleyball": 890, + "vulture": 23, + "waffle iron": 891, + "walking stick, walkingstick, stick insect": 313, + "wall clock": 892, + "wallaby, brush kangaroo": 104, + "wallet, billfold, notecase, pocketbook": 893, + "wardrobe, closet, press": 894, + "warplane, military plane": 895, + "warthog": 343, + "washbasin, handbasin, washbowl, lavabo, wash-hand basin": 896, + "washer, automatic washer, washing machine": 897, + "water bottle": 898, + "water buffalo, water ox, Asiatic buffalo, Bubalus bubalis": 346, + "water jug": 899, + "water ouzel, dipper": 20, + "water snake": 58, + "water tower": 900, + "weasel": 356, + "web site, website, internet site, site": 916, + "weevil": 307, + "whippet": 172, + "whiptail, whiptail lizard": 41, + "whiskey jug": 901, + "whistle": 902, + "white stork, Ciconia ciconia": 127, + "white wolf, Arctic wolf, Canis lupus tundrarum": 270, + "wig": 903, + "wild boar, boar, Sus scrofa": 342, + "window screen": 904, + "window shade": 905, + "wine bottle": 907, + "wing": 908, + "wire-haired fox terrier": 188, + "wok": 909, + "wolf spider, hunting spider": 77, + "wombat": 106, + "wood rabbit, cottontail, cottontail rabbit": 330, + "wooden spoon": 910, + "wool, woolen, woollen": 911, + "worm fence, snake fence, snake-rail fence, Virginia fence": 912, + "wreck": 913, + "yawl": 914, + "yellow lady's slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum": 986, + "yurt": 915, + "zebra": 340, + "zucchini, courgette": 939 + }, + "layer_norm_eps": 1e-05, + "mlp_ratio": 2.0, + "model_type": "mobilevit", + "neck_hidden_sizes": [ + 4, + 8, + 16, + 24, + 32, + 40, + 160 + ], + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mobilevit", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 2, + "num_channels": 3, + "output_stride": 32, + "patch_size": 2, + "qkv_bias": true, + "semantic_loss_ignore_index": 255 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/mpnet/hf-internal-testing/tiny-random-MPNetModel/a86ba94b3903ec685a95.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/mpnet/hf-internal-testing/tiny-random-MPNetModel/a86ba94b3903ec685a95.json new file mode 100644 index 0000000000000000000000000000000000000000..01f20a789a70131fdc28dc7b16064ecbdba45d7f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/mpnet/hf-internal-testing/tiny-random-MPNetModel/a86ba94b3903ec685a95.json @@ -0,0 +1,41 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-MPNetModel", + "_task": "token-classification", + "architectures": [ + "MPNetModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 64, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "mpnet", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "mpnet", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "relative_attention_num_buckets": 32, + "vocab_size": 1125 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/phi3/yujiepan/phi-4-tiny-random/b74fb7c3d127d2361d6a.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/phi3/yujiepan/phi-4-tiny-random/b74fb7c3d127d2361d6a.json new file mode 100644 index 0000000000000000000000000000000000000000..cb9e911cb4e3dc2da5d66b430bfe9cd59a9d2df6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/phi3/yujiepan/phi-4-tiny-random/b74fb7c3d127d2361d6a.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "dtype": "bfloat16", + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "partial_rotary_factor": 1.0, + "rope_theta": 250000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/b52ba06aa5dd84b77765.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/b52ba06aa5dd84b77765.json new file mode 100644 index 0000000000000000000000000000000000000000..b5987fb20ae98e5a2f37dee7f9fa75a7d1f7b544 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/b52ba06aa5dd84b77765.json @@ -0,0 +1,65 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "layer_types": [ + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_theta": 1000000.0, + "rope_type": "yarn", + "type": "yarn" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/e65562ca1ac02dd41d5c.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/e65562ca1ac02dd41d5c.json new file mode 100644 index 0000000000000000000000000000000000000000..d435389b76856f4d9a1f51c6cbcaaa31a82bb0ca --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/e65562ca1ac02dd41d5c.json @@ -0,0 +1,68 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "_task": "text-generation", + "architectures": [ + "Qwen3MoeForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "decoder_sparse_step": 2, + "dtype": "float32", + "head_dim": 32, + "hidden_act": "silu", + "hidden_size": 64, + "initializer_range": 0.02, + "intermediate_size": 128, + "max_position_embeddings": 40960, + "max_window_layers": 1, + "mlp_only_layers": [], + "model_type": "qwen3_moe", + "moe_intermediate_size": 128, + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "optimum-internal-testing/tiny-random-qwen3_moe", + "checkpoint_revision": "e0230be2839556b44b7400a233c73c74b4abb7af", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float32", + "tp_degree": 2 + }, + "norm_topk_prob": true, + "num_attention_heads": 2, + "num_experts_per_tok": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "router_aux_loss_coef": 0.001, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/roberta/hf-internal-testing/tiny-random-RobertaModel/253af4a9a064191237a9.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/roberta/hf-internal-testing/tiny-random-RobertaModel/253af4a9a064191237a9.json new file mode 100644 index 0000000000000000000000000000000000000000..d53b8b62ace1b4f1f5c78cc42324fcf6aeb91d9b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/roberta/hf-internal-testing/tiny-random-RobertaModel/253af4a9a064191237a9.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RobertaModel", + "_task": "token-classification", + "architectures": [ + "RobertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "dtype": "float32", + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "position_embedding_type": "absolute", + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 1024 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/roformer/hf-internal-testing/tiny-random-RoFormerModel/58d796b9cd3b8d7bfb9e.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/roformer/hf-internal-testing/tiny-random-RoFormerModel/58d796b9cd3b8d7bfb9e.json new file mode 100644 index 0000000000000000000000000000000000000000..d05b7eb9c1cf7a07bbe8045d517f9a9d3235f816 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/roformer/hf-internal-testing/tiny-random-RoFormerModel/58d796b9cd3b8d7bfb9e.json @@ -0,0 +1,44 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-RoFormerModel", + "_task": "token-classification", + "architectures": [ + "RoFormerModel" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "embedding_size": 32, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "roformer", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "roformer", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "rotary_value": false, + "type_vocab_size": 16, + "use_cache": true, + "vocab_size": 50000 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/fa0c3c4b4d230ee3d726.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/fa0c3c4b4d230ee3d726.json new file mode 100644 index 0000000000000000000000000000000000000000..7afd2edc88accb964d354d8bf81deb9e676bfb27 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/fa0c3c4b4d230ee3d726.json @@ -0,0 +1,138 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolLM3-3B", + "_task": "text-generation", + "architectures": [ + "SmolLM3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 65536, + "max_window_layers": 28, + "mlp_bias": false, + "model_type": "smollm3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolLM3-3B", + "checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layer_interval": 4, + "no_rope_layers": [ + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 4, + "pretraining_tp": 2, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 5000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/stable-diffusion/hf-internal-testing/tiny-stable-diffusion-torch/4cf01c220325f9c0461a.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/stable-diffusion/hf-internal-testing/tiny-stable-diffusion-torch/4cf01c220325f9c0461a.json new file mode 100644 index 0000000000000000000000000000000000000000..08639645a6779288d5429b9c589a19d227e70004 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/stable-diffusion/hf-internal-testing/tiny-stable-diffusion-torch/4cf01c220325f9c0461a.json @@ -0,0 +1,125 @@ +{ + "_entry_class": "MultiModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-stable-diffusion-torch", + "_task": null, + "text_encoder": { + "architectures": [ + "CLIPTextModel" + ], + "attention_dropout": 0.0, + "dropout": 0.0, + "dtype": "float32", + "export_model_type": "clip-text-model", + "hidden_act": "quick_gelu", + "hidden_size": 32, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 77, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "vocab_size": 1000 + }, + "unet": { + "_class_name": "UNet2DConditionModel", + "act_fn": "silu", + "addition_embed_type": null, + "addition_embed_type_num_heads": 64, + "addition_time_embed_dim": null, + "attention_head_dim": 8, + "attention_type": "default", + "block_out_channels": [ + 32, + 64 + ], + "center_input_sample": false, + "class_embed_type": null, + "class_embeddings_concat": false, + "conv_in_kernel": 3, + "conv_out_kernel": 3, + "cross_attention_dim": 32, + "cross_attention_norm": null, + "down_block_types": [ + "DownBlock2D", + "CrossAttnDownBlock2D" + ], + "downsample_padding": 1, + "dropout": 0.0, + "dual_cross_attention": false, + "encoder_hid_dim": null, + "encoder_hid_dim_type": null, + "flip_sin_to_cos": true, + "freq_shift": 0, + "in_channels": 4, + "layers_per_block": 2, + "mid_block_only_cross_attention": null, + "mid_block_scale_factor": 1, + "mid_block_type": "UNetMidBlock2DCrossAttn", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 32, + "static_num_channels": 4, + "static_sequence_length": 77, + "static_vae_scale_factor": 2, + "static_width": 32, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_eps": 1e-05, + "norm_num_groups": 32, + "num_attention_heads": null, + "num_class_embeds": null, + "only_cross_attention": false, + "out_channels": 4, + "output_attentions": false, + "projection_class_embeddings_input_dim": null, + "resnet_out_scale_factor": 1.0, + "resnet_skip_time_act": false, + "resnet_time_scale_shift": "default", + "reverse_transformer_layers_per_block": null, + "time_cond_proj_dim": null, + "time_embedding_act_fn": null, + "time_embedding_dim": null, + "time_embedding_type": "positional", + "timestep_post_act": null, + "transformer_layers_per_block": 1, + "up_block_types": [ + "CrossAttnUpBlock2D", + "UpBlock2D" + ], + "upcast_attention": false, + "use_linear_projection": false + } +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/vit/hf-internal-testing/tiny-random-vit/c46019d4d1ceee4d1b9f.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/vit/hf-internal-testing/tiny-random-vit/c46019d4d1ceee4d1b9f.json new file mode 100644 index 0000000000000000000000000000000000000000..461c860907be0022135797a804a060f0983fc136 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/vit/hf-internal-testing/tiny-random-vit/c46019d4d1ceee4d1b9f.json @@ -0,0 +1,45 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-vit", + "_task": "image-classification", + "architectures": [ + "ViTForImageClassification" + ], + "attention_probs_dropout_prob": 0.1, + "dtype": "float32", + "encoder_stride": 16, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "image_size": 30, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "model_type": "vit", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "vit", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "task": "image-classification", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_channels": 3, + "num_hidden_layers": 5, + "patch_size": 2, + "pooler_act": "tanh", + "pooler_output_size": 32, + "qkv_bias": true, + "vocab_size": {} +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/wav2vec2/hf-internal-testing/tiny-random-Wav2Vec2Model/2731814c90335f8ff3cb.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/wav2vec2/hf-internal-testing/tiny-random-Wav2Vec2Model/2731814c90335f8ff3cb.json new file mode 100644 index 0000000000000000000000000000000000000000..60b79754471c0c4b5a50e84eb0aa6ea396c5c5b5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/wav2vec2/hf-internal-testing/tiny-random-Wav2Vec2Model/2731814c90335f8ff3cb.json @@ -0,0 +1,105 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-Wav2Vec2Model", + "_task": "automatic-speech-recognition", + "activation_dropout": 0.1, + "adapter_attn_dim": null, + "adapter_kernel_size": 3, + "adapter_stride": 2, + "add_adapter": false, + "apply_spec_augment": true, + "architectures": [ + "Wav2Vec2Model" + ], + "attention_dropout": 0.1, + "classifier_proj_size": 256, + "codevector_dim": 256, + "contrastive_logits_temperature": 0.1, + "conv_bias": false, + "conv_dim": [ + 32, + 32, + 32 + ], + "conv_kernel": [ + 8, + 8, + 8 + ], + "conv_stride": [ + 4, + 4, + 4 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "diversity_loss_weight": 0.1, + "do_stable_layer_norm": false, + "dtype": "float32", + "feat_extract_activation": "gelu", + "feat_extract_dropout": 0.0, + "feat_extract_norm": "group", + "feat_proj_dropout": 0.0, + "feat_quantizer_dropout": 0.0, + "final_dropout": 0.1, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_dropout_prob": 0.1, + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 20, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "mask_feature_length": 10, + "mask_feature_min_masks": 0, + "mask_feature_prob": 0.0, + "mask_time_length": 2, + "mask_time_min_masks": 2, + "mask_time_prob": 0.5, + "model_type": "wav2vec2", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "wav2vec2", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_audio_sequence_length": 100000, + "static_batch_size": 1, + "task": "automatic-speech-recognition", + "tensor_parallel_size": 1 + }, + "num_adapter_layers": 1, + "num_attention_heads": 2, + "num_codevector_groups": 2, + "num_codevectors_per_group": 320, + "num_conv_pos_embedding_groups": 2, + "num_conv_pos_embeddings": 16, + "num_feat_extract_layers": 3, + "num_hidden_layers": 4, + "num_negatives": 100, + "output_hidden_size": 16, + "proj_codevector_dim": 256, + "tdnn_dilation": [ + 1, + 2 + ], + "tdnn_dim": [ + 32, + 32 + ], + "tdnn_kernel": [ + 5, + 3 + ], + "use_weighted_layer_sum": false, + "vocab_size": 32, + "xvector_output_dim": 32 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/xlm-roberta/hf-internal-testing/tiny-xlm-roberta/c33ee1c0b1397f908a2c.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/xlm-roberta/hf-internal-testing/tiny-xlm-roberta/c33ee1c0b1397f908a2c.json new file mode 100644 index 0000000000000000000000000000000000000000..bd811c631699cde9202dcc17bf8f26253451afcd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/xlm-roberta/hf-internal-testing/tiny-xlm-roberta/c33ee1c0b1397f908a2c.json @@ -0,0 +1,56 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-xlm-roberta", + "_task": "fill-mask", + "add_cross_attention": false, + "architectures": [ + "XLMRobertaForCausalLM" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "d_ff": 256, + "d_kv": 8, + "d_model": 64, + "dtype": "float32", + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 256, + "initializer_range": 0.02, + "intermediate_size": 256, + "is_decoder": false, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 64, + "model_type": "xlm-roberta", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "xlm-roberta", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 32, + "task": "fill-mask", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 2, + "num_decoder_layers": 2, + "num_heads": 2, + "num_hidden_layers": 2, + "num_layers": 2, + "output_past": true, + "position_embedding_type": "absolute", + "relative_attention_num_buckets": 32, + "tie_word_embeddings": true, + "type_vocab_size": 1, + "use_cache": true, + "vocab_size": 5002 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/xlm/hf-internal-testing/tiny-random-XLMModel/e9c92f51c5852325ab39.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/xlm/hf-internal-testing/tiny-random-XLMModel/e9c92f51c5852325ab39.json new file mode 100644 index 0000000000000000000000000000000000000000..3e49857eb477c074f052baf44949fa10e946ad5d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/xlm/hf-internal-testing/tiny-random-XLMModel/e9c92f51c5852325ab39.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-XLMModel", + "_task": "token-classification", + "architectures": [ + "XLMModel" + ], + "asm": false, + "attention_dropout": 0.1, + "bos_index": 0, + "causal": false, + "dropout": 0.1, + "dtype": "float32", + "emb_dim": 32, + "embed_init_std": 0.02209708691207961, + "end_n_top": 5, + "eos_index": 1, + "gelu_activation": true, + "init_std": 0.02, + "initializer_range": 0.02, + "is_encoder": true, + "lang_id": 0, + "layer_norm_eps": 1e-12, + "mask_index": 5, + "mask_token_id": 5, + "max_position_embeddings": 512, + "model_type": "xlm", + "n_heads": 4, + "n_langs": 2, + "n_layers": 5, + "n_special": 0, + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "xlm", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 128, + "task": "token-classification", + "tensor_parallel_size": 1 + }, + "pad_index": 2, + "sinusoidal_embeddings": false, + "start_n_top": 5, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "last", + "summary_use_proj": true, + "unk_index": 3, + "use_lang_emb": true, + "use_proj": true, + "vocab_size": 30145 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/yolos/hf-internal-testing/tiny-random-YolosModel/1a5a3fbb3fbe346f29ed.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/yolos/hf-internal-testing/tiny-random-YolosModel/1a5a3fbb3fbe346f29ed.json new file mode 100644 index 0000000000000000000000000000000000000000..7edc09d4ebbfe6623f140bf4bd4576410963aada --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/yolos/hf-internal-testing/tiny-random-YolosModel/1a5a3fbb3fbe346f29ed.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-YolosModel", + "_task": "object-detection", + "architectures": [ + "YolosModel" + ], + "attention_probs_dropout_prob": 0.1, + "auxiliary_loss": false, + "bbox_cost": 5, + "bbox_loss_coefficient": 5, + "class_cost": 1, + "dtype": "float32", + "eos_coefficient": 0.1, + "giou_cost": 2, + "giou_loss_coefficient": 2, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1", + "2": "LABEL_2" + }, + "image_size": [ + 30, + 30 + ], + "initializer_range": 0.02, + "intermediate_size": 37, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1, + "LABEL_2": 2 + }, + "layer_norm_eps": 1e-12, + "model_type": "yolos", + "neuron": { + "auto_cast": null, + "auto_cast_type": null, + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": true, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "trn1", + "int_dtype": "int64", + "model_type": "yolos", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "task": "object-detection", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_channels": 3, + "num_detection_tokens": 10, + "num_hidden_layers": 5, + "patch_size": 2, + "qkv_bias": true, + "use_mid_position_embeddings": true +} \ No newline at end of file