| { | |
| "architectures": [ | |
| "TinyLlavaForConditionalGeneration" | |
| ], | |
| "cache_dir": null, | |
| "connector_type": "blp_4i_2x", | |
| "hidden_size": 4096, | |
| "ignore_index": -100, | |
| "image_aspect_ratio": "audio", | |
| "image_token_index": -200, | |
| "llm_model_name_or_path": "Qwen/Qwen3-8B-Base", | |
| "model_type": "tinyllava", | |
| "auto_map": { | |
| "AutoConfig": "configuration.TinyLlavaConfig", | |
| "AutoModelForCausalLM": "modeling_mufun.TinyLlavaForConditionalGeneration" | |
| }, | |
| "num_queries": 128, | |
| "num_resampler_layers": 3, | |
| "pad_token": "<|endoftext|>", | |
| "resampler_hidden_size": 768, | |
| "text_config": { | |
| "_attn_implementation_autoset": true, | |
| "_name_or_path": "Qwen/Qwen3-8B-Base", | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151643, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 36, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": null, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| }, | |
| "tokenizer_model_max_length": 32768, | |
| "tokenizer_name_or_path": "Qwen/Qwen3-8B-Base", | |
| "tokenizer_padding_side": "right", | |
| "tokenizer_use_fast": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.3", | |
| "tune_type_connector": "full", | |
| "tune_type_llm": "full", | |
| "tune_type_vision_tower": "full", | |
| "tune_vision_tower_from_layer": 0, | |
| "use_cache": false, | |
| "vision_config": { | |
| "_name_or_path": "openai/whisper-large-v3", | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "apply_spec_augment": false, | |
| "architectures": [ | |
| "WhisperForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "begin_suppress_tokens": [ | |
| 220, | |
| 50257 | |
| ], | |
| "bos_token_id": 50257, | |
| "classifier_proj_size": 256, | |
| "d_model": 1280, | |
| "decoder_attention_heads": 20, | |
| "decoder_ffn_dim": 5120, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 32, | |
| "decoder_start_token_id": 50258, | |
| "dropout": 0.0, | |
| "encoder_attention_heads": 20, | |
| "encoder_ffn_dim": 5120, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 32, | |
| "eos_token_id": 50257, | |
| "init_std": 0.02, | |
| "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, | |
| "model_name_or_path": "openai/whisper-large-v3", | |
| "model_name_or_path2": "", | |
| "model_type": "whisper", | |
| "num_hidden_layers": 32, | |
| "num_mel_bins": 128, | |
| "scale_embedding": false, | |
| "torch_dtype": "float16", | |
| "use_cache": true, | |
| "use_weighted_layer_sum": false, | |
| "vocab_size": 51866 | |
| }, | |
| "vision_feature_layer": -2, | |
| "vision_feature_select_strategy": "patch", | |
| "vision_hidden_size": 1280, | |
| "vision_model_name_or_path": "openai/whisper-large-v3", | |
| "vision_model_name_or_path2": "", | |
| "vocab_size": 151936 | |
| } | |