Publish owned visual language baseline with complete assets and measured limitations
6aa5569 verified | { | |
| "config": { | |
| "architecture_version": 1, | |
| "foundation_source": { | |
| "repo_id": "HuggingFaceTB/SmolVLM-256M-Instruct", | |
| "revision": "7e3e67edbbed1bf9888184d9df282b700a323964" | |
| }, | |
| "freeze_foundation": true, | |
| "generation_config": { | |
| "_from_model_config": true, | |
| "assistant_confidence_threshold": null, | |
| "assistant_early_exit": null, | |
| "assistant_ensemble_weight": null, | |
| "assistant_lookbehind": null, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": 0, | |
| "cache_config": null, | |
| "cache_implementation": null, | |
| "compile_config": null, | |
| "constraints": null, | |
| "continuous_batching_config": null, | |
| "decoder_start_token_id": null, | |
| "disable_compile": null, | |
| "diversity_penalty": null, | |
| "do_sample": null, | |
| "dola_layers": null, | |
| "early_stopping": null, | |
| "encoder_no_repeat_ngram_size": null, | |
| "encoder_repetition_penalty": null, | |
| "eos_token_id": 49279, | |
| "epsilon_cutoff": null, | |
| "eta_cutoff": null, | |
| "exponential_decay_length_penalty": null, | |
| "force_words_ids": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "guidance_scale": null, | |
| "is_assistant": null, | |
| "length_penalty": null, | |
| "low_memory": null, | |
| "max_cache_len": null, | |
| "max_length": null, | |
| "max_matching_ngram_size": null, | |
| "max_new_tokens": null, | |
| "max_time": null, | |
| "min_length": null, | |
| "min_new_tokens": null, | |
| "min_p": null, | |
| "no_repeat_ngram_size": null, | |
| "num_assistant_tokens": null, | |
| "num_assistant_tokens_schedule": null, | |
| "num_beam_groups": null, | |
| "num_beams": null, | |
| "num_return_sequences": null, | |
| "output_attentions": null, | |
| "output_hidden_states": null, | |
| "output_logits": null, | |
| "output_scores": null, | |
| "pad_token_id": 2, | |
| "penalty_alpha": null, | |
| "prefill_chunk_size": null, | |
| "prompt_lookup_num_tokens": null, | |
| "remove_invalid_values": null, | |
| "renormalize_logits": null, | |
| "repetition_penalty": null, | |
| "return_dict_in_generate": null, | |
| "sequence_bias": null, | |
| "speculation_type": null, | |
| "stop_strings": null, | |
| "suppress_tokens": null, | |
| "target_lookbehind": null, | |
| "temperature": null, | |
| "token_healing": null, | |
| "top_h": null, | |
| "top_k": null, | |
| "top_p": null, | |
| "transformers_version": "5.17.0", | |
| "typical_p": null, | |
| "use_cache": null, | |
| "use_mtp": null, | |
| "watermarking_config": null | |
| }, | |
| "language_config": { | |
| "_name_or_path": "HuggingFaceTB/SmolVLM-256M-Instruct", | |
| "architectures": [ | |
| "Idefics3ForConditionalGeneration" | |
| ], | |
| "chunk_size_feed_forward": 0, | |
| "dtype": "float32", | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_token_id": 49190, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "model_type": "idefics3", | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "pad_token_id": 128002, | |
| "problem_type": null, | |
| "return_dict": true, | |
| "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, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "dtype": "float32", | |
| "eos_token_id": 2, | |
| "finetuning_task": null, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 576, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.041666666666666664, | |
| "intermediate_size": 1536, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "is_llama_config": true, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "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, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "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, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "qk_layer_norms": false, | |
| "return_dict": true, | |
| "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" | |
| } | |
| }, | |
| "transformers_version": "5.17.0", | |
| "use_cache": true, | |
| "vision_config": { | |
| "_attn_implementation_autoset": false, | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "dtype": "float32", | |
| "eos_token_id": null, | |
| "finetuning_task": null, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_size": 512, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "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, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "pad_token_id": null, | |
| "patch_size": 16, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "return_dict": true, | |
| "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 | |
| }, | |
| "max_image_size": 4096, | |
| "max_input_tokens": 4096, | |
| "max_new_tokens": 256, | |
| "max_question_chars": 4096, | |
| "max_target_chars": 4096, | |
| "mode": "language", | |
| "processor_hashes": { | |
| "chat_template.jinja": "830005085ddd94cec605b6e21b885b28ffad6e3f82ee6a212c523533e8f04f01", | |
| "processor_config.json": "10ed91fcba8f9a8c6c2a1f7ac83d3a13ef1db7664dbcf21825354090c92e865d", | |
| "tokenizer.json": "2500f374cdc89040032a7d8437b6ed0fe745667b1194c17914d062ee31701605", | |
| "tokenizer_config.json": "bc02954797389e5218643004c85428053aec98f8b7d977b7cd3e8054b491d23e" | |
| }, | |
| "workspace_dimensions": 64, | |
| "workspace_slots": 8, | |
| "workspace_steps": 2 | |
| }, | |
| "format": "tensorcode.pretrained", | |
| "tool": "tensorcode.tools.scene.Scene", | |
| "version": 1 | |
| } | |