Could you provide the images.zip file of the gpt4v-dataset? I have collected all the other datasets, but I can't find this one.

[cheng-haha]

No description provided.

[cheng-haha]

In fact, my machine can not connected to the Internet, so I can't download pictures during training.

[cheng-haha]

Similar problems have not been solved either: issues35

[zs-zhong]

Apologies for the late response! Since this dataset is quite large, you can try downloading it from this link: https://github.com/InternLM/InternLM-XComposer/blob/main/projects/ShareGPT4V/docs/Data.md.
Alternatively, let me know which specific images are missing. If not too many, I can package and upload them for you.

[cheng-haha]

Thank you very much. I have already downloaded gpt4v-dataset from Hugging Face. Although some images are still missing, it shouldn't be a significant issue. Currently, I have trained Stage 2, but I only have the LoRA weights. How can I execute the script to obtain a CKPT similar to Lyra-Mini-3B? This is because I want to run lyra_chartvqa_speech.sh, but the script don't save the complete CKPT.

[zs-zhong]

Hi, I’m going to close this issue as it seems to be resolved. If you have any further questions or concerns, feel free to reopen the discussion or create a new issue. Thanks!