{ "architectures": [ "HfMoondream" ], "auto_map": { "AutoConfig": "hf_moondream.HfConfig", "AutoModelForCausalLM": "hf_moondream.HfMoondream" }, "config": {}, "dtype": "bfloat16", "model_type": "moondream1", "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": true, "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" }, "transformers_version": "5.3.0" }