diffusers/Qwen-Image-Layered-modular

1{2  "architectures": [3    "Qwen2_5_VLForConditionalGeneration"4  ],5  "attention_dropout": 0.0,6  "bos_token_id": 151643,7  "dtype": "float16",8  "eos_token_id": 151645,9  "hidden_act": "silu",10  "hidden_size": 3584,11  "image_token_id": 151655,12  "initializer_range": 0.02,13  "intermediate_size": 18944,14  "max_position_embeddings": 128000,15  "max_window_layers": 28,16  "model_type": "qwen2_5_vl",17  "num_attention_heads": 28,18  "num_hidden_layers": 28,19  "num_key_value_heads": 4,20  "quantization_config": {21    "_load_in_4bit": true,22    "_load_in_8bit": false,23    "bnb_4bit_compute_dtype": "bfloat16",24    "bnb_4bit_quant_storage": "uint8",25    "bnb_4bit_quant_type": "nf4",26    "bnb_4bit_use_double_quant": false,27    "llm_int8_enable_fp32_cpu_offload": false,28    "llm_int8_has_fp16_weight": false,29    "llm_int8_skip_modules": null,30    "llm_int8_threshold": 6.0,31    "load_in_4bit": true,32    "load_in_8bit": false,33    "quant_method": "bitsandbytes"34  },35  "rms_norm_eps": 1e-06,36  "rope_scaling": {37    "mrope_section": [38      16,39      24,40      2441    ],42    "rope_type": "default",43    "type": "default"44  },45  "rope_theta": 1000000.0,46  "sliding_window": 32768,47  "text_config": {48    "_name_or_path": "OzzyGT/qwen-image-layered-bnb-4bit-text-encoder",49    "architectures": [50      "Qwen2_5_VLForConditionalGeneration"51    ],52    "attention_dropout": 0.0,53    "bos_token_id": 151643,54    "dtype": "float16",55    "eos_token_id": 151645,56    "hidden_act": "silu",57    "hidden_size": 3584,58    "initializer_range": 0.02,59    "intermediate_size": 18944,60    "layer_types": [61      "full_attention",62      "full_attention",63      "full_attention",64      "full_attention",65      "full_attention",66      "full_attention",67      "full_attention",68      "full_attention",69      "full_attention",70      "full_attention",71      "full_attention",72      "full_attention",73      "full_attention",74      "full_attention",75      "full_attention",76      "full_attention",77      "full_attention",78      "full_attention",79      "full_attention",80      "full_attention",81      "full_attention",82      "full_attention",83      "full_attention",84      "full_attention",85      "full_attention",86      "full_attention",87      "full_attention",88      "full_attention"89    ],90    "max_position_embeddings": 128000,91    "max_window_layers": 28,92    "model_type": "qwen2_5_vl_text",93    "num_attention_heads": 28,94    "num_hidden_layers": 28,95    "num_key_value_heads": 4,96    "rms_norm_eps": 1e-06,97    "rope_scaling": {98      "mrope_section": [99        16,100        24,101        24102      ],103      "rope_type": "default",104      "type": "default"105    },106    "rope_theta": 1000000.0,107    "sliding_window": null,108    "use_cache": true,109    "use_sliding_window": false,110    "vision_token_id": 151654,111    "vocab_size": 152064112  },113  "tie_word_embeddings": false,114  "transformers_version": "4.57.3",115  "use_cache": true,116  "use_sliding_window": false,117  "video_token_id": 151656,118  "vision_config": {119    "depth": 32,120    "dtype": "float16",121    "fullatt_block_indexes": [122      7,123      15,124      23,125      31126    ],127    "hidden_act": "silu",128    "hidden_size": 1280,129    "in_channels": 3,130    "in_chans": 3,131    "initializer_range": 0.02,132    "intermediate_size": 3420,133    "model_type": "qwen2_5_vl",134    "num_heads": 16,135    "out_hidden_size": 3584,136    "patch_size": 14,137    "spatial_merge_size": 2,138    "spatial_patch_size": 14,139    "temporal_patch_size": 2,140    "tokens_per_second": 2,141    "window_size": 112142  },143  "vision_end_token_id": 151653,144  "vision_start_token_id": 151652,145  "vision_token_id": 151654,146  "vocab_size": 152064147}148