{ "architectures": [ "Qwen3AVLForConditionalGeneration" ], "auto_map": { "AutoConfig": "configuration_qwen3_avl.Qwen3AVLConfig", "AutoModel": "modeling_qwen3_avl.Qwen3AVLModel", "AutoModelForCausalLM": "modeling_qwen3_avl.Qwen3AVLForConditionalGeneration" }, "audio_config": { "_name_or_path": "whisper_ft", "activation_dropout": 0.0, "activation_function": "gelu", "apply_spec_augment": false, "architectures": [ "WhisperForConditionalGeneration" ], "attention_dropout": 0.0, "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": 4, "decoder_start_token_id": 50258, "dropout": 0.0, "dtype": "bfloat16", "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_source_positions": 1500, "max_target_positions": 448, "median_filter_width": 7, "model_type": "whisper", "num_hidden_layers": 32, "num_mel_bins": 128, "pad_token_id": 151643, "scale_embedding": false, "tie_word_embeddings": true, "use_cache": false, "use_weighted_layer_sum": false, "vocab_size": 51866 }, "audio_end_token_id": 151671, "audio_start_token_id": 151670, "audio_token_id": 151669, "bos_token_id": null, "deepstack_audio_indexes": [ 8, 16, 24 ], "dtype": "bfloat16", "eos_token_id": 151645, "hidden_size": 4096, "image_token_id": 151655, "model_type": "qwen3_vl", "pad_token_id": 151643, "text_config": { "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "dtype": "bfloat16", "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 12288, "max_position_embeddings": 262144, "model_type": "qwen3_vl_text", "num_attention_heads": 32, "num_hidden_layers": 36, "num_key_value_heads": 8, "pad_token_id": 151643, "rms_norm_eps": 1e-06, "rope_parameters": { "mrope_interleaved": true, "mrope_section": [ 24, 20, 20 ], "rope_theta": 5000000, "rope_type": "default" }, "tie_word_embeddings": false, "use_cache": false, "vocab_size": 151936 }, "tie_word_embeddings": false, "transformers_version": "5.2.0.dev0", "use_cache": false, "video_token_id": 151656, "vision_config": { "deepstack_visual_indexes": [ 8, 16, 24 ], "depth": 27, "dtype": "bfloat16", "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1152, "in_channels": 3, "initializer_range": 0.02, "intermediate_size": 4304, "model_type": "qwen3_vl", "num_heads": 16, "num_position_embeddings": 2304, "out_hidden_size": 4096, "pad_token_id": 151643, "patch_size": 16, "spatial_merge_size": 2, "temporal_patch_size": 2 }, "vision_end_token_id": 151653, "vision_start_token_id": 151652 }