config.json

{
  "_name_or_path": "/data1/xly/models/Qwen-1_8B",
  "architectures": [
    "LlavaQWenForCausalLM"
  ],
  "attn_dropout_prob": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_qwen.QWenConfig",
    "AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel"
  },
  "bf16": true,
  "emb_dropout_prob": 0.0,
  "fp16": false,
  "fp32": false,
  "freeze_mm_mlp_adapter": false,
  "hidden_size": 2048,
  "image_aspect_ratio": "pad",
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "kv_channels": 128,
  "layer_norm_epsilon": 1e-06,
  "max_position_embeddings": 8192,
  "mm_hidden_size": 1024,
  "mm_projector_lr": null,
  "mm_projector_type": "mlp2x_gelu",
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
  "model_type": "qwen",
  "no_bias": true,
  "num_attention_heads": 16,
  "num_hidden_layers": 24,
  "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",
  "tokenizer_model_max_length": 2048,
  "tokenizer_padding_side": "right",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.31.0",
  "tune_mm_mlp_adapter": false,
  "use_cache": true,
  "use_cache_kernel": false,
  "use_cache_quantization": false,
  "use_dynamic_ntk": true,
  "use_flash_attn": "auto",
  "use_logn_attn": true,
  "use_mm_proj": true,
  "vocab_size": 151936
}