{ "architectures": ["MistralForCausalLM"], "hidden_size": 4096, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "num_attention_heads": 32, "num_hidden_layers": 32, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "vocab_size": 32000 }