REILX
/

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

Image-Text-to-Text

txtimage-to-txt

Inference Endpoints

Model card Files Files and versions Community

REILX commited on Jul 9

Commit

9ae916c

•

1 Parent(s): adfd125

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -11,7 +11,7 @@ tags:
 - lora
 ---
-### 模型 llava-Qwen2-7B-Instruct-CLIP-ZH 增强中文文字识别能力和表情包内涵识别能力
 1. 模型结构：</br>
 llava-Qwen2-7B-Instruct-CLIP-ZH = Qwen/Qwen2-7B-Instruct + multi_modal_projector + openai/clip-vit-large-patch14-336</br>

 - lora
 ---
+### 模型 llava-Qwen2-7B-Instruct-CLIP-ZH 增强中文文字识别能力和表情包内涵识别能力，达到gpt4o、claude-3.5-sonnet的能力！！！！！
 1. 模型结构：</br>
 llava-Qwen2-7B-Instruct-CLIP-ZH = Qwen/Qwen2-7B-Instruct + multi_modal_projector + openai/clip-vit-large-patch14-336</br>