{ "_name_or_path": "deepseek-ai/deepseek-vl-1.3b-chat", "aligner_config": { "cls": "MlpProjector", "model_type": "aligner", "params": { "depth": 2, "input_dim": 1024, "n_embed": 2048, "projector_type": "mlp_gelu" } }, "architectures": [ "MultiModalityCausalLM" ], "language_config": { "hidden_size": 2048, "intermediate_size": 5632, "max_position_embeddings": 16384, "model_type": "llama", "num_attention_heads": 16, "num_hidden_layers": 24, "num_key_value_heads": 16, "torch_dtype": "float16", "vocab_size": 102400 }, "model_type": "multi_modality", "quantization_config": { "_load_in_4bit": true, "_load_in_8bit": false, "bnb_4bit_compute_dtype": "float16", "bnb_4bit_quant_storage": "uint8", "bnb_4bit_quant_type": "nf4", "bnb_4bit_use_double_quant": false, "llm_int8_enable_fp32_cpu_offload": false, "llm_int8_has_fp16_weight": false, "llm_int8_skip_modules": null, "llm_int8_threshold": 6.0, "load_in_4bit": true, "load_in_8bit": false, "quant_method": "bitsandbytes" }, "torch_dtype": "float16", "transformers_version": "4.44.2", "vision_config": { "cls": "CLIPVisionTower", "model_type": "vision", "params": { "image_size": 384, "model_name": "siglip_large_patch16_384", "pixel_mean": [ 0.5, 0.5, 0.5 ], "pixel_std": [ 0.5, 0.5, 0.5 ], "select_feature": "same", "select_layer": -1 } } }