2132660698

Results 25 comments of 2132660698

[Bug]: text_image_search cannot run in an offline environment

![image](https://user-images.githubusercontent.com/94035926/179342232-fc379aaf-8e84-4312-9326-7e6c4b8fb67c.png) copy all ~/.towhee files (online mechine run ok) to the offline environment.

Support for InternVL

+1

[Question] a100 80g单卡训练还 out of memory

请问能说一下data_dir下面的训练语料有多少吗？什么格式截个图，谢谢！

InternVL-1.5 希望可以支持

同求，感谢！

InternVL可以支持一下微调不

+1

Thanks for your feedback! Can u retry the latest version?

![image](https://github.com/InternLM/InternLM-XComposer/assets/94035926/31b0be32-83d6-4f71-bba6-caab9c86fe3d)

Thanks for your feedback! Can u retry the latest version?

![image](https://github.com/InternLM/InternLM-XComposer/assets/94035926/710f8b27-795b-4423-9ded-604665d51c7d)

Thanks for your feedback! Can u retry the latest version?

这是我的微调数据，这个数据微调internlm-xcomposer2-vl-7b没有问题。 ![image](https://github.com/InternLM/InternLM-XComposer/assets/94035926/21897ce6-d7c8-48c6-b655-ba72b1883839)

Thanks for your feedback! Can u retry the latest version?

> This issue is due to the current 4khd fine-tuning code does not support multiple images in one query. Please stay tuned. 应该是你说的这个情况，将训练数据中的多图改成一张图后，可以Lora训练完成。

Thanks for your feedback! Can u retry the latest version?

请问Lora训练后，可以合并吗？