{ "_commit_hash": null, "_name_or_path": "/mnt/petrelfs/wangweiyun/workspace_zjg/InternVL-Code2/internvl_chat_dev/work_dirs/vitlarge_whisperlarge_internlm7b_pretrain_ASR_visionstage3_d240729_audiodecay0p95_6144_1e-4_26m_vlcodebase", "architectures": [ "InternVLChatAudioModel" ], "audio_config": { "_name_or_path": "openai/whisper-large-v3", "activation_dropout": 0.0, "activation_function": "gelu", "add_cross_attention": false, "apply_spec_augment": false, "architectures": [ "WhisperForConditionalGeneration" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": [ 220, 50257 ], "bos_token_id": 50257, "chunk_size_feed_forward": 0, "classifier_proj_size": 256, "cross_attention_hidden_size": null, "d_model": 1280, "decoder_attention_heads": 20, "decoder_ffn_dim": 5120, "decoder_layerdrop": 0.0, "decoder_layers": 32, "decoder_start_token_id": 50258, "diversity_penalty": 0.0, "do_sample": false, "dropout": 0.0, "early_stopping": false, "encoder_attention_heads": 20, "encoder_ffn_dim": 5120, "encoder_layerdrop": 0.0, "encoder_layers": 32, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 50257, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "init_std": 0.02, "is_decoder": false, "is_encoder_decoder": true, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "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": 448, "max_source_positions": 1500, "max_target_positions": 448, "median_filter_width": 7, "min_length": 0, "model_type": "whisper", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 32, "num_mel_bins": 128, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 50256, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "scale_embedding": 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": "float16", "torchscript": false, "transformers_version": "4.37.2", "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "use_weighted_layer_sum": false, "vocab_size": 51866 }, "downsample_ratio": 0.5, "dynamic_image_size": true, "force_image_size": 448, "llm_config": { "_name_or_path": "./pretrained/internlm2_5-7b-chat", "add_cross_attention": false, "architectures": [ "InternLM2ForCausalLM" ], "attn_implementation": "flash_attention_2", "auto_map": { "AutoConfig": "configuration_internlm2.InternLM2Config", "AutoModel": "modeling_internlm2.InternLM2ForCausalLM", "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM" }, "bad_words_ids": null, "begin_suppress_tokens": null, "bias": false, "bos_token_id": 1, "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": 2, "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": 32768, "min_length": 0, "model_type": "internlm2", "no_repeat_ngram_size": 0, "num_attention_heads": 32, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 32, "num_key_value_heads": 8, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 2, "prefix": null, "pretraining_tp": 1, "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": 2.0, "type": "dynamic" }, "rope_theta": 1000000, "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": null, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.37.2", "typical_p": 1.0, "use_bfloat16": true, "use_cache": false, "vocab_size": 92556 }, "max_dynamic_patch": 6, "min_dynamic_patch": 1, "model_type": "internvl_chat", "pad2square": false, "ps_version": "v2", "select_layer": -1, "template": "internlm2-chat", "torch_dtype": "bfloat16", "transformers_version": null, "use_backbone_lora": 0, "use_llm_lora": 0, "use_thumbnail": true, "vision_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "InternVisionModel" ], "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, "drop_path_rate": 0.1, "dropout": 0.0, "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": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 448, "initializer_factor": 1.0, "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-06, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "intern_vit_6b", "no_repeat_ngram_size": 0, "norm_type": "layer_norm", "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 24, "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": {}, "qk_normalization": false, "qkv_bias": true, "remove_invalid_values": false, "repetition_penalty": 1.0, "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": null, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.37.2", "typical_p": 1.0, "use_bfloat16": true, "use_flash_attn": true } }