| { | |
| "anyres": false, | |
| "architectures": [ | |
| "HCXVisionV2ForCausalLM" | |
| ], | |
| "audio_config": { | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "Qwen2AudioEncoder" | |
| ], | |
| "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, | |
| "d_model": 1280, | |
| "decoder_start_token_id": null, | |
| "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": null, | |
| "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, | |
| "initializer_range": 0.02, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_source_positions": 1500, | |
| "min_length": 0, | |
| "model_type": "qwen2_audio_encoder", | |
| "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": null, | |
| "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": "float32", | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false | |
| }, | |
| "audio_model_name_or_path": null, | |
| "audio_projector_type": "mlp", | |
| "audio_start_id": 128071, | |
| "audio_token_id": 128071, | |
| "auto_map": { | |
| "AutoConfig": "configuration_vlm.HCXVisionConfig", | |
| "AutoModelForCausalLM": "modeling_vlm.HCXVisionForCausalLM", | |
| "AutoModelForSequenceClassification": "modeling_vlm.HCXVisionForSequenceClassification" | |
| }, | |
| "discrete_audio_config": { | |
| "model_name_or_path": null, | |
| "model_type": "cosyvoice2", | |
| "torch_dtype": "float32" | |
| }, | |
| "discrete_audio_model_name_or_path": null, | |
| "discrete_audio_start_id": 128074, | |
| "discrete_audio_token_id": 128074, | |
| "discrete_audio_unit_0_id": 128606, | |
| "discrete_image_start_id": 128069, | |
| "discrete_image_token_id": 128069, | |
| "discrete_image_unit_0_id": 135168, | |
| "discrete_vision_config": { | |
| "model_name_or_path": null, | |
| "model_type": "ta_tok", | |
| "torch_dtype": "float32" | |
| }, | |
| "discrete_vision_model_name_or_path": null, | |
| "end_token_id": 128001, | |
| "eos_token_id": 128001, | |
| "freeze_audio_projector": true, | |
| "freeze_before_sampler": false, | |
| "freeze_decoder": false, | |
| "freeze_encoder": true, | |
| "freeze_mm_projector": false, | |
| "freeze_video_audio_compressor": false, | |
| "hidden_size": 4096, | |
| "ignore_index": -100, | |
| "image_token_id": 128062, | |
| "img_start_id": 128062, | |
| "is_safetensor_save": true, | |
| "max_num_grids": -1, | |
| "mm_projector_type": "linear", | |
| "model_type": "vlm", | |
| "num_queries_vis_abstractor": -1, | |
| "possible_resolutions": [], | |
| "proj_pos_emb": true, | |
| "proj_prenorm": false, | |
| "q_former_model_name_or_path": null, | |
| "text_config": { | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": 128000, | |
| "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": 128001, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "logits_scaling": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 8192, | |
| "min_length": 0, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 32, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "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-06, | |
| "rope_scaling": null, | |
| "rope_theta": 5000000, | |
| "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": "float32", | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "vocab_size": 200704 | |
| }, | |
| "text_model_name_or_path": null, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.52.4", | |
| "unpad": false, | |
| "use_1x1_grid": false, | |
| "use_nth_layer": -2, | |
| "video_audio_compressor_type": "mambamia", | |
| "video_audio_start_id": 128070, | |
| "video_audio_token_id": 128070, | |
| "video_first_last_frames_slows": null, | |
| "video_max_num_frames": 120, | |
| "video_num_queries_fast": null, | |
| "video_num_queries_slow": null, | |
| "video_start_id": 128063, | |
| "video_token_id": 128063, | |
| "vision_config": { | |
| "add_cross_attention": false, | |
| "anyres": false, | |
| "architectures": [ | |
| "Qwen2_5_VisionTransformerPretrainedModel" | |
| ], | |
| "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, | |
| "depth": 32, | |
| "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, | |
| "fullatt_block_indexes": [ | |
| 7, | |
| 15, | |
| 23, | |
| 31 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 1280, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "in_channels": 3, | |
| "in_chans": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3456, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_num_grids": -1, | |
| "min_length": 0, | |
| "model_type": "qwen2_5_vl", | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_heads": 16, | |
| "num_return_sequences": 1, | |
| "out_hidden_size": 5120, | |
| "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, | |
| "spatial_merge_size": 2, | |
| "spatial_patch_size": 14, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "temporal_patch_size": 2, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "tokens_per_second": 2, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": "float32", | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "window_size": 112 | |
| }, | |
| "vision_input_chunk_size": null, | |
| "vision_model_name_or_path": null | |
| } | |