{
  "_name_or_path": "/mmu_kg_ssd/zhaizepeng/kuaizhi/code-main/KuaiChain/230421-InstructTuning/6-tongyi/train/1104-1/saved_model/Qwen_7b_5e-6",
  "architectures": [
    "QWenLMHeadModel"
  ],
  "attn_dropout_prob": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_qwen.QWenConfig",
    "AutoModel": "modeling_qwen.QWenLMHeadModel",
    "AutoModelForCausalLM": "Qwen/Qwen-7B-Chat--modeling_qwen.QWenLMHeadModel"
  },
  "bf16": true,
  "emb_dropout_prob": 0.0,
  "fp16": false,
  "fp32": false,
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 22016,
  "kv_channels": 128,
  "layer_norm_epsilon": 1e-06,
  "max_position_embeddings": 8192,
  "model_type": "qwen",
  "no_bias": true,
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "onnx_safe": null,
  "rotary_emb_base": 10000,
  "rotary_pct": 1.0,
  "scale_attn_weights": true,
  "seq_length": 8192,
  "softmax_in_fp32": false,
  "tie_word_embeddings": false,
  "tokenizer_class": "QWenTokenizer",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.33.2",
  "use_cache": false,
  "use_cache_kernel": false,
  "use_cache_quantization": false,
  "use_dynamic_ntk": true,
  "use_flash_attn": true,
  "use_logn_attn": true,
  "vocab_size": 151936
}