{
  "_name_or_path": "NousResearch/Llama-2-13b-chat-hf",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 13824,
  "max_position_embeddings": 4096,
  "model_type": "llama",
  "neuron": {
    "auto_cast_type": "fp16",
    "batch_size": 1,
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.11.0.34+c5231f848",
    "num_cores": 32,
    "sequence_length": 2048,
    "task": "text-generation"
  },
  "num_attention_heads": 40,
  "num_hidden_layers": 40,
  "num_key_value_heads": 40,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.35.0",
  "use_cache": true,
  "vocab_size": 32000
}