Zhe Chen
Hello, thanks for your advice. The fine-tuning script for InternVL2-76B has been uploaded.
请问您的lmdeploy版本是什么，可以升级到v0.5.2再试试
@ErfeiCui Please take a look at their application.
Hello, thank you for contributing to our repository. We will proceed with the merge after conducting some tests. Thanks again!
您好，视频可以预处理成图片进行输入
您好，您可以尝试在每次推理结束后都运行`torch.cuda.empty_cache()`，会清空每次计算产生的显存。
Hi, since there hasn't been any recent activity on this issue, I'll be closing it for now. If it's still an active concern, don't hesitate to reopen it. Thanks for...
您好，感谢您的反馈。我推荐使用新的Streamlit demo进行部署：https://internvl.readthedocs.io/en/latest/get_started/local_chat_demo.html#streamlit-demo
请问这个问题解决了吗？可能是因为爆显存了
This issue is likely due to noisy data in the previous model’s training set, causing occasional repetition of sentences. We've trained the new InternVL 2.5 model to reduce this behavior....