{ "architectures": [ "MistralForCausalLM" ], "model_type": "mistral", "torch_dtype": "float16", "transformers_version": "4.36.0", "vocab_size": 32000, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "max_position_embeddings": 32768, "initializer_range": 0.02, "rms_norm_eps": 1e-05, "use_cache": true, "rope_theta": 10000.0, "sliding_window": 4096, "attention_dropout": 0.0 }