qwen/config.json

{
  "architectures": [
    "QWenLMHeadModel"
  ],
  "auto_map": {
    "AutoConfig": "configuration_qwen.QWenConfig",
    "AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel"
  },
  "attn_dropout_prob": 0.0,
  "bf16": false,
  "emb_dropout_prob": 0.0,
  "fp16": true,
  "fp32": false,
  "hidden_size": 5120,
  "intermediate_size": 27392,
  "initializer_range": 0.02,
  "kv_channels": 128,
  "layer_norm_epsilon": 1e-06,
  "max_position_embeddings": 8192,
  "model_type": "qwen",
  "no_bias": true,
  "num_attention_heads": 40,
  "num_hidden_layers": 40,
  "onnx_safe": null,
  "quantization_config": {
    "bits": 4,
    "group_size": 128,
    "damp_percent": 0.01,
    "desc_act": false,
    "static_groups": false,
    "sym": true,
    "true_sequential": true,
    "model_name_or_path": null,
    "model_file_base_name": "model",
    "quant_method": "gptq"
  },
  "rotary_emb_base": 10000,
  "rotary_pct": 1.0,
  "scale_attn_weights": true,
  "seq_length": 8192,
  "tie_word_embeddings": false,
  "tokenizer_class": "QWenTokenizer",
  "transformers_version": "4.32.0",
  "use_cache": true,
  "use_dynamic_ntk": true,
  "use_flash_attn": "auto",
  "use_logn_attn": true,
  "vocab_size": 152064
}