simonJJJ commited on
Commit
7ce5bb5
1 Parent(s): 9783357

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -44,7 +44,7 @@ inference: false
44
  如果想了解更多关于模型的信息,请点击[链接](https://github.com/QwenLM/Qwen-VL/blob/master/visual_memo.md)查看我们的技术备忘录。
45
 
46
  We release two models of the Qwen-VL series:
47
- - Qwen-VL: The pre-trained LVLM model uses Qwen-7B as the initialization of the LLM, and [Openclip ViT-bigG](https://github.com/mlfoundations/open_clip) as the initialization of the visual encoder. And connects them with a randomly initialized cross-attention layer. Qwen-VL was trained on about 1.5B image-text paired data. The final image input resolution is 448.
48
  - Qwen-VL-Chat: A multimodal LLM-based AI assistant, which is trained with alignment techniques.
49
 
50
  For more details about Qwen-VL, please refer to our [technical memo](https://github.com/QwenLM/Qwen-VL/blob/master/visual_memo.md).
 
44
  如果想了解更多关于模型的信息,请点击[链接](https://github.com/QwenLM/Qwen-VL/blob/master/visual_memo.md)查看我们的技术备忘录。
45
 
46
  We release two models of the Qwen-VL series:
47
+ - Qwen-VL: The pre-trained LVLM model uses Qwen-7B as the initialization of the LLM, and [Openclip ViT-bigG](https://github.com/mlfoundations/open_clip) as the initialization of the visual encoder. And connects them with a randomly initialized cross-attention layer. Qwen-VL was trained on about 1.5B image-text paired data.
48
  - Qwen-VL-Chat: A multimodal LLM-based AI assistant, which is trained with alignment techniques.
49
 
50
  For more details about Qwen-VL, please refer to our [technical memo](https://github.com/QwenLM/Qwen-VL/blob/master/visual_memo.md).