{ "architectures": [ "Qwen2_5_VLForConditionalGeneration" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 3584, "image_token_id": 151655, "initializer_range": 0.02, "intermediate_size": 18944, "max_position_embeddings": 128000, "max_window_layers": 28, "model_type": "qwen2_5_vl", "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "quantization_config": { "autoround_version": "0.6.1.dev", "bits": 4, "block_name_to_quantize": "model.language_model.layers", "data_type": "int", "extra_config": { "model.visual.blocks.0.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.0.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.1.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.1.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.10.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.10.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.11.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.11.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.12.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.12.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.13.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.13.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.14.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.14.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.15.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.15.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.16.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.16.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.17.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.17.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.18.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.18.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.19.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.19.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.2.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.2.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.20.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.20.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.21.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.21.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.22.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.22.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.23.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.23.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.24.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.24.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.25.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.25.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.26.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.26.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.27.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.27.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.28.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.28.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.29.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.29.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.3.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.3.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.30.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.30.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.31.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.31.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.4.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.4.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.5.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.5.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.6.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.6.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.7.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.7.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.8.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.8.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.9.attn.proj": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.blocks.9.attn.qkv": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.merger.mlp.0": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true }, "model.visual.merger.mlp.2": { "bits": 8, "data_type": "int", "group_size": 128, "sym": true } }, "group_size": 128, "packing_format": "auto_round:auto_gptq", "quant_method": "auto-round", "sym": true }, "rms_norm_eps": 1e-06, "rope_scaling": { "mrope_section": [ 16, 24, 24 ], "rope_type": "default", "type": "default" }, "rope_theta": 1000000.0, "sliding_window": 32768, "text_config": { "architectures": [ "Qwen2_5_VLForConditionalGeneration" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 3584, "image_token_id": null, "initializer_range": 0.02, "intermediate_size": 18944, "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", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 128000, "max_window_layers": 28, "model_type": "qwen2_5_vl_text", "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_scaling": { "mrope_section": [ 16, 24, 24 ], "rope_type": "default", "type": "default" }, "rope_theta": 1000000.0, "sliding_window": null, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "video_token_id": null, "vision_end_token_id": 151653, "vision_start_token_id": 151652, "vision_token_id": 151654, "vocab_size": 152064 }, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.53.2", "use_cache": true, "use_sliding_window": false, "video_token_id": 151656, "vision_config": { "depth": 32, "fullatt_block_indexes": [ 7, 15, 23, 31 ], "hidden_act": "silu", "hidden_size": 1280, "in_channels": 3, "in_chans": 3, "initializer_range": 0.02, "intermediate_size": 3420, "model_type": "qwen2_5_vl", "num_heads": 16, "out_hidden_size": 3584, "patch_size": 14, "spatial_merge_size": 2, "spatial_patch_size": 14, "temporal_patch_size": 2, "tokens_per_second": 2, "window_size": 112 }, "vision_end_token_id": 151653, "vision_start_token_id": 151652, "vision_token_id": 151654, "vocab_size": 152064 }