{ "architectures": [ "Llama3ForConditionalGeneration" ], "audio_config": { "_attn_implementation_autoset": true, "_attn_implementation": "eager", "_name_or_path": "", "activation_dropout": 0.0, "adapter_act": "relu", "adapter_kernel_size": 7, "adapter_stride": 4, "add_adapter": true, "add_cross_attention": false, "apply_spec_augment": false, "architectures": [ "Wav2Vec2BertModel" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 1, "chunk_size_feed_forward": 0, "classifier_proj_size": 768, "codevector_dim": 768, "conformer_conv_dropout": 0.1, "contrastive_logits_temperature": 0.1, "conv_depthwise_kernel_size": 31, "cross_attention_hidden_size": null, "ctc_loss_reduction": "sum", "ctc_zero_infinity": false, "decoder_start_token_id": null, "diversity_loss_weight": 0.1, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 2, "exponential_decay_length_penalty": null, "feat_proj_dropout": 0.0, "feat_quantizer_dropout": 0.0, "feature_projection_input_dim": 160, "final_dropout": 0.1, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "swish", "hidden_dropout": 0.0, "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-05, "layerdrop": 0.1, "left_max_position_embeddings": 64, "length_penalty": 1.0, "mask_feature_length": 10, "mask_feature_min_masks": 0, "mask_feature_prob": 0.0, "mask_time_length": 10, "mask_time_min_masks": 2, "mask_time_prob": 0.05, "max_length": 20, "max_source_positions": 5000, "min_length": 0, "model_type": "wav2vec2-bert", "no_repeat_ngram_size": 0, "num_adapter_layers": 1, "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_codevector_groups": 2, "num_codevectors_per_group": 320, "num_hidden_layers": 24, "num_negatives": 100, "num_return_sequences": 1, "output_attentions": false, "output_hidden_size": 4096, "output_hidden_states": false, "output_scores": false, "pad_token_id": 0, "position_embeddings_type": "relative_key", "prefix": null, "problem_type": null, "proj_codevector_dim": 768, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "right_max_position_embeddings": 8, "rotary_embedding_base": 10000, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "tdnn_dilation": [ 1, 2, 3, 1, 1 ], "tdnn_dim": [ 512, 512, 512, 512, 1500 ], "tdnn_kernel": [ 5, 3, 3, 1, 1 ], "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "float16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_intermediate_ffn_before_adapter": false, "use_weighted_layer_sum": false, "vocab_size": 128256, "xvector_output_dim": 512 }, "audio_token_index": 128257, "auto_map": { "AutoConfig": "configuration_llama3.Llama3Config", "AutoModel": "modeling_llama3.Llama3ForConditionalGeneration", "AutoProcessor": "processing_mllama.MllamaProcessor", "AutoFeatureExtractor": "audio_processing_mllama.MllamaAudioFeatureExtractor" }, "image_token_index": 128256, "model_type": "llama3", "text_config": { "_attn_implementation_autoset": false, "_name_or_path": "", "add_cross_attention": false, "architectures": null, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 128000, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "cross_attention_layers": [ 3, 8, 13, 18, 23, 28, 33, 38 ], "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "dropout": 0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": [ 128001, 128008, 128009 ], "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 4096, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 14336, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 131072, "min_length": 0, "model_type": "mllama_text_model", "no_repeat_ngram_size": 0, "num_attention_heads": 32, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 40, "num_key_value_heads": 8, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 128004, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3" }, "rope_theta": 500000.0, "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": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "float16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 128256 }, "torch_dtype": "float16", "transformers_version": "4.46.0", "vision_config": { "_attn_implementation_autoset": false, "_name_or_path": "", "add_cross_attention": false, "architectures": null, "attention_heads": 16, "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": "gelu", "hidden_size": 1280, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 560, "initializer_range": 0.02, "intermediate_layers_indices": [ 3, 7, 15, 23, 30 ], "intermediate_size": 5120, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_num_tiles": 4, "min_length": 0, "model_type": "mllama_vision_model", "no_repeat_ngram_size": 0, "norm_eps": 1e-05, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_global_layers": 8, "num_hidden_layers": 32, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "supported_aspect_ratios": [ [ 1, 1 ], [ 1, 2 ], [ 1, 3 ], [ 1, 4 ], [ 2, 1 ], [ 2, 2 ], [ 3, 1 ], [ 4, 1 ] ], "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": "float16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "vision_output_dim": 7680 } }