{ "architectures": [ "MistralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 4096, "model_type": "mistral", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "quantization_config": { "amp": false, "autoround_version": "0.15.1", "bits": 4, "damp_percent": 0.01, "data_type": "int", "desc_act": false, "group_size": 64, "lm_head": false, "provider": "auto-round", "quant_method": "gptq", "static_attention_granularity": "tensor", "static_kv_granularity": "tensor", "sym": false, "true_sequential": false }, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.55.3", "use_cache": false, "vocab_size": 51200 }