{ "_name_or_path": "Qwen/Qwen2-VL-2B-Instruct", "architectures": [ "Qwen2VLForConditionalGeneration" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 1536, "image_token_id": 151655, "initializer_range": 0.02, "intermediate_size": 8960, "max_position_embeddings": 32768, "max_window_layers": 28, "model_type": "qwen2_vl", "num_attention_heads": 12, "num_hidden_layers": 28, "num_key_value_heads": 2, "pad_token_id": 151654, "quantization_config": { "_load_in_4bit": true, "_load_in_8bit": false, "bnb_4bit_compute_dtype": "bfloat16", "bnb_4bit_quant_storage": "uint8", "bnb_4bit_quant_type": "nf4", "bnb_4bit_use_double_quant": true, "llm_int8_enable_fp32_cpu_offload": false, "llm_int8_has_fp16_weight": false, "llm_int8_skip_modules": [ "lm_head", "multi_modal_projector", "merger", "modality_projection", "visual.blocks.0.mlp", "visual.blocks.1.mlp", "visual.blocks.2.mlp", "visual.blocks.3.mlp", "visual.blocks.4.mlp", "visual.blocks.5.mlp", "visual.blocks.6.mlp", "visual.blocks.7.mlp", "visual.blocks.8.mlp", "visual.blocks.9.mlp", "visual.blocks.10.mlp", "visual.blocks.11.mlp", "visual.blocks.12.mlp", "visual.blocks.13.mlp", "visual.blocks.14.mlp", "visual.blocks.15.mlp", "visual.blocks.16.mlp", "visual.blocks.17.mlp", "visual.blocks.18.mlp", "visual.blocks.19.mlp", "visual.blocks.20.mlp", "visual.blocks.21.mlp", "visual.blocks.22.mlp", "visual.blocks.23.mlp", "visual.blocks.24.mlp", "visual.blocks.25.mlp", "visual.blocks.26.mlp", "visual.blocks.27.mlp", "visual.blocks.28.mlp", "visual.blocks.29.mlp", "visual.blocks.30.mlp", "visual.blocks.31.mlp" ], "llm_int8_threshold": 6.0, "load_in_4bit": true, "load_in_8bit": false, "quant_method": "bitsandbytes" }, "rms_norm_eps": 1e-06, "rope_scaling": { "mrope_section": [ 16, 24, 24 ], "rope_type": "default", "type": "default" }, "rope_theta": 1000000.0, "sliding_window": 32768, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.46.3", "unsloth_fixed": true, "use_cache": true, "use_sliding_window": false, "video_token_id": 151656, "vision_config": { "hidden_size": 1536, "in_chans": 3, "model_type": "qwen2_vl", "spatial_patch_size": 14 }, "vision_end_token_id": 151653, "vision_start_token_id": 151652, "vision_token_id": 151654, "vocab_size": 151936 }