{ "transformers_version": "5.9.0", "architectures": [ "Qwen2VLDiffusionForConditionalGeneration" ], "dtype": "bfloat16", "text_config": { "architectures": [ "Qwen2VLForConditionalGeneration" ], "dtype": "bfloat16", "vocab_size": 151936, "hidden_size": 896, "intermediate_size": 4864, "num_hidden_layers": 24, "num_attention_heads": 14, "num_key_value_heads": 2, "hidden_act": "silu", "max_position_embeddings": 8192, "initializer_range": 0.02, "rms_norm_eps": 1e-06, "use_cache": false, "use_sliding_window": false, "sliding_window": null, "max_window_layers": 24, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "attention_dropout": 0.0, "rope_parameters": { "mrope_section": [ 8, 12, 12 ], "rope_type": "default", "type": "default", "rope_theta": 1000000.0 }, "bos_token_id": 151643, "eos_token_id": 151645, "pad_token_id": 151643, "tie_word_embeddings": true, "vision_token_id": 151654, "model_type": "qwen2_vl_text" }, "vision_config": { "dtype": "bfloat16", "depth": 32, "embed_dim": 1280, "hidden_size": 896, "hidden_act": "quick_gelu", "mlp_ratio": 4, "num_heads": 16, "in_channels": 3, "patch_size": 14, "spatial_merge_size": 2, "temporal_patch_size": 2, "initializer_range": 0.02, "in_chans": 3, "pad_token_id": 151643, "spatial_patch_size": 14, "model_type": "qwen2_vl_vision" }, "image_token_id": 151655, "video_token_id": 151656, "vision_start_token_id": 151652, "vision_end_token_id": 151653, "tie_word_embeddings": true, "model_type": "qwen2vl_diffusion", "vision_token_id": 151654, "auto_map": { "AutoConfig": "configuration_qwen2vl_diffusion.Qwen2VLDiffusionConfig", "AutoModel": "modeling_qwen2vl_diffusion.Qwen2VLDiffusionModel", "AutoModelForCausalLM": "modeling_qwen2vl_diffusion.Qwen2VLDiffusionForConditionalGeneration", "AutoModelForImageTextToText": "modeling_qwen2vl_diffusion.Qwen2VLDiffusionForConditionalGeneration" }, "diffusion": { "mask_token": "<|mask|>", "mask_token_id": 151674, "block_size": 16, "denoising_steps": 16, "attention_mask_mode": "prefix_causal_block_full", "generation_mode": "block_diffusion" } }