{
  "architectures": ["MistralForCausalLM"],
  "model_type": "mistral",
  "hidden_size": 4096,
  "intermediate_size": 14336,
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "vocab_size": 32000,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "use_cache": true,
  "rope_theta": 10000.0
}