Skip to content

Issues: haotian-liu/LLaVA

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

1,023 Open 542 Closed
1,023 Open 542 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[Question] How do I set the image input to a null value?
#1814 opened Dec 23, 2024 by rickeyhhh
[Usage] Cannot Launch a gradio web server
#1812 opened Dec 17, 2024 by LiuChang-ao
使用finetune_task_lora.sh微调llava_1.5模型无法运行
#1811 opened Dec 17, 2024 by zhangye0402
[Question] Abnormal Generation after finetuning ONLY single label classification dataset
#1796 opened Dec 11, 2024 by enkaranfiles
[Question] How do you fine-tune LLaVA-NeXT on video data?
#1795 opened Dec 11, 2024 by DrVictorBenjamin
1
[Usage] peft 1.40.0 requires transformers at least 0.47
#1794 opened Dec 11, 2024 by shtu-ryan
[Question] Why does text-only data use the empty image token?
#1792 opened Dec 9, 2024 by MSungK
Issue with 4-bit Quantization for LLaVA-NeXT-Video-32B Model on A100-40GB GPU
#1791 opened Dec 7, 2024 by Rachel0901
[Question] When I reproduced the second stage using finetune.sh, the processing time per image was too slow
#1790 opened Dec 5, 2024 by TanmouTT
1
[Question] Fintune llava-v1.5-7b just use all textvqa data, but get Accuracy: 0.00%
#1789 opened Dec 4, 2024 by ethanyys
[Question] grad_norm=None
#1787 opened Dec 3, 2024 by Pixel-anter
[Question] demo website error https://llava.hliu.cc/
#1786 opened Nov 27, 2024 by zkailinzhang
[Question] llava 预训练中断，继续预训练默认加载模型报错
#1785 opened Nov 27, 2024 by cqray1990
[Question] Model parameters during finetuning (prints me only mm_projector parameters)
#1784 opened Nov 26, 2024 by daulettoibazar
1
[Question] Does llava support dynamic image tokens input?
#1783 opened Nov 26, 2024 by hktk07
[Discussion] loss function of finetune llava 1.5 with sft
#1782 opened Nov 25, 2024 by bollossom
[Question] when run v1.5/pretrain.sh , there are some errors
#1780 opened Nov 24, 2024 by cqray1990
[Question] pretrain data
#1779 opened Nov 24, 2024 by cqray1990
[Question] I trained the llava-1.5-13B model, but when evaluating, the inference answer is always empty and the speed is very slow.
#1778 opened Nov 23, 2024 by ykzqjyhhh
[Usage] Batch evaluation using sqlang doesn't support llava-v1.5 model
#1777 opened Nov 23, 2024 by pspdada
[Question] Where can I obtain the training dataset of the LLava 1.5?
#1776 opened Nov 20, 2024 by weiaicunzai
1
[Usage] json.decoder.JSONDecodeError: Expecting ',' delimiter: line 1559608 column 82 (char 39444904)
#1775 opened Nov 18, 2024 by tianke0711
[Question] Image-text match
#1774 opened Nov 18, 2024 by hazardout
[Usage] The issue encountered when fine-tuning llava_mistral1.6 using LoRA
#1772 opened Nov 16, 2024 by yuwang4321
[Usage] Infer on model finetuned using finetune_qlora.sh
#1771 opened Nov 16, 2024 by amagzari
1
ProTip! Find all open issues with in progress development work with linked:pr.