{
  "_name_or_path": "llama-13b-hf-35q_4bit-128g_WVU_",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "bos_token_id": 0,
  "eos_token_id": 1,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 13824,
  "max_position_embeddings": 2048,
  "max_sequence_length": 2048,
  "model_type": "llama",
  "num_attention_heads": 40,
  "num_hidden_layers": 40,
  "pad_token_id": -1,
  "quant_bits": 4,
  "quant_groupsize": 128,
  "quant_layers": 35,
  "rms_norm_eps": 1e-06,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.29.2",
  "use_cache": true,
  "vocab_size": 32000
}