{ "architectures": [ "Qwen3VLStitchedForH3Conditioning" ], "auto_map": { "AutoConfig": "configuration_qwen3_vl_stitched.Qwen3VLStitchedConfig", "AutoModel": "modeling_qwen3_vl_stitched.Qwen3VLStitchedForH3Conditioning" }, "bridge_config": { "expand_v": 2.0, "head_dim": 64, "input_features": 4096, "max_log_gain": 2.0, "mode": "chunk", "num_heads": 6, "num_lanes": 4, "output_features": 5120, "output_head_reference_width": 512, "use_short_conv": true, "width": 512 }, "dtype": "bfloat16", "model_type": "qwen3_vl_stitched_h3", "output_layer": 50, "source_config": { "architectures": [ "Qwen3VLForConditionalGeneration" ], "image_token_id": 151655, "model_type": "qwen3_vl", "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, "rms_norm_eps": 1e-06, "rope_scaling": { "mrope_interleaved": true, "mrope_section": [ 24, 20, 20 ], "rope_type": "default" }, "rope_theta": 5000000, "use_cache": false, "vocab_size": 151936 }, "tie_word_embeddings": false, "video_token_id": 151656, "vision_config": { "deepstack_visual_indexes": [ 8, 16, 24 ], "depth": 27, "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, "patch_size": 16, "spatial_merge_size": 2, "temporal_patch_size": 2 }, "vision_end_token_id": 151653, "vision_start_token_id": 151652 }, "source_layer": 16, "source_model_name": "Qwen/Qwen3-VL-8B-Instruct", "target_layer": 29, "target_model_name": "Qwen/Qwen3-VL-32B-Instruct", "target_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": 5120, "initializer_range": 0.02, "intermediate_size": 25600, "max_position_embeddings": 262144, "model_type": "qwen3_vl_text", "num_attention_heads": 64, "num_hidden_layers": 64, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_scaling": { "mrope_interleaved": true, "mrope_section": [ 24, 20, 20 ], "rope_type": "default" }, "rope_theta": 5000000, "use_cache": false, "vocab_size": 151936 }, "transformers_version": "5.15.0", "use_cache": false }