Synchronizing local compiler cache.

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+  }
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+  }
+}

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
+}

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
+  }
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}

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
+}