Hugging Face's logo

REILX
/
llava-Qwen2-7B-Instruct-Chinese-CLIP

Image-Text-to-Text
Transformers
Safetensors
Chinese
llava
pretraining
Qwen2
txtimage-to-txt
lora
conversational
Inference Endpoints
Model card Files Community
REILX commited on
Commit
1e9841e
•
1 Parent(s): a601509

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -37,6 +37,10 @@ llava-Qwen2-7B-Instruct-CLIP-ZH = Qwen/Qwen2-7B-Instruct + multi_modal_projector
37
  ![](./images/llava-qwen2-lora-02.JPG)
38
  ![](./images/llava-qwen2-lora-03.JPG)
39
 
 
 
 
 
40
 
41
  5. 代码</br>
42
  合并模型代码，合并模型之后将add_tokens.json,merge.txt,preprocessor_config.json,specital_token_map.json,tokenizer.json,vocab.json文件复制到"/保存的完整模型路径"。
 
37
  ![](./images/llava-qwen2-lora-02.JPG)
38
  ![](./images/llava-qwen2-lora-03.JPG)
39
 
40
+ 对比gpt4o的识别效果</br>
41
+ ![](./images/gpt4o-01.JPG)
42
+ ![](./images/gpt4o-02.JPG)
43
+ ![](./images/gpt4o-03.JPG)
44
 
45
  5. 代码</br>
46
  合并模型代码，合并模型之后将add_tokens.json,merge.txt,preprocessor_config.json,specital_token_map.json,tokenizer.json,vocab.json文件复制到"/保存的完整模型路径"。