{
  "_name_or_path": "./",
  "architectures": [
    "QWenLMHeadModel"
  ],
  "llm_pretrained_model_name_or_path": "qwen/qwen-7b",
  "attn_dropout_prob": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_qwen.QWenConfig",
    "AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel"
  },
  "emb_dropout_prob": 0.0,
  "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": 2048,
  "tie_word_embeddings": false,
  "tokenizer_type": "QWenTokenizer",
  "dtype": "bfloat16",
  "transformers_version": "4.31.0",
  "use_cache": true,
  "recompute": true,
  "use_dynamic_ntk": true,
  "use_flash_attn": false,
  "use_logn_attn": true,
  "use_flash_attention": true,
  "use_fused_rms_norm": true,
  "use_fused_rope": true,
  "visual": {
    "heads": 16,
    "image_size": 448,
    "image_start_id": 151857,
    "layers": 48,
    "mlp_ratio": 4.9231,
    "output_dim": 4096,
    "patch_size": 14,
    "width": 1664
  },
  "vocab_size": 151936
}