{
  "_name_or_path": "../../../basemodels/Yarn-Llama-2-13b-64k",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_llama.LlamaConfig",
    "AutoModelForCausalLM": "modeling_llama.LlamaForCausalLM"
  },
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 13824,
  "max_position_embeddings": 65536,
  "model_type": "llama",
  "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": {
    "factor": 16.0,
    "original_max_position_embeddings": 4096,
    "type": "yarn"
  },
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.33.0.dev0",
  "use_cache": true,
  "use_flash_attention": false,
  "vocab_size": 32000,
  "quantization_config": {
    "quant_method": "awq",
    "zero_point": true,
    "group_size": 128,
    "bits": 4,
    "version": "gemm"
  }
}