{
  "_name_or_path": "/mnt/llm_dataset/libinbin/xverse_65b/LLaMA-Megatron/checkpoint/65b-2.5t-stage2-turbo_40w_clean/pretrain_PP1_new/iter_0000639/mp_rank_00/",
  "architectures": [
    "XverseForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_xverse.XverseConfig",
    "AutoModelForCausalLM": "modeling_xverse.XverseForCausalLM"
  },
  "bos_token_id": 2,
  "eos_token_id": 3,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 22016,
  "max_position_embeddings": 16384,
  "max_tokenizer_truncation": 16384,
  "model_type": "xverse",
  "num_attention_heads": 64,
  "num_hidden_layers": 80,
  "pad_token_id": 1,
  "quantization_config": {
    "bits": 8,
    "damp_percent": 0.01,
    "desc_act": true,
    "group_size": 128,
    "is_marlin_format": false,
    "model_file_base_name": null,
    "model_name_or_path": null,
    "quant_method": "gptq",
    "static_groups": true,
    "sym": true,
    "true_sequential": true
  },
  "rms_norm_eps": 1e-06,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.39.1",
  "use_cache": true,
  "vocab_size": 100534
}