{ "_name_or_path": "mistralai/Mistral-Large-Instruct-2407", "architectures": [ "MistralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 12288, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 131072, "model_type": "mistral", "num_attention_heads": 96, "num_hidden_layers": 88, "num_key_value_heads": 8, "quantization_config": { "bits": 4, "checkpoint_format": "gptq", "damp_percent": 0.05, "desc_act": true, "exponent_hinv": 4.0, "group_size": 128, "model_file_base_name": null, "model_name_or_path": null, "quant_method": "gptq", "shrink": 0.0625, "static_groups": false, "sym": false, "true_sequential": true }, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.45.2", "use_cache": true, "vocab_size": 32768 }