Skip to content

Issues: haotian-liu/LLaVA

Beta
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

1,071 Open 550 Closed
1,071 Open 550 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[Usage] feat: add power-law decay loss option to finetune
#1881 opened May 23, 2025 by shaojintian
[Usage] Broken Url
#1879 opened May 14, 2025 by Ora-Kool
[Feature request] Compatibility between zero3 and pretrain_mm_mlp_adapter
#1878 opened May 13, 2025 by ZarkPanda
[Usage] CUDA out-of-memory when running plain LLaVA inference on RTX 4090
#1877 opened May 12, 2025 by omerbgu1
[Question] How to Quantize LLaVA model
#1876 opened May 12, 2025 by Himanshunitrr
[Question] How can I fine-tune all components in LLaVA — the vision encoder, projector, and LLM (using lora)?
#1875 opened May 9, 2025 by SFaegheh
[Usage] Resume from checkpoint during training with LoRA.
#1874 opened May 2, 2025 by keanshi-nlp
[Usage] Where can I find weights for Vicuna-v1.6 adapter
#1873 opened Apr 30, 2025 by rishi2002
"There was a problem with multiple GPU inference in last year's LLaVA 1.6 — any updates?"
#1870 opened Apr 15, 2025 by fabio1shot
[Question] What is huggingface address for LLaVA-v1.5-LLaMA3-8B model?
#1869 opened Apr 14, 2025 by qm-intel
[Question] Why does LengthGroupSampler ensure that all samples in the same batch are from the same modality, either text or image?
#1867 opened Apr 9, 2025 by UnableToUseGit
[Usage] fastapi version PydanticSchema GenerationError
#1866 opened Apr 9, 2025 by Jack1447
[Question] Is the LLaVA-1.5-HD model not open source?
#1865 opened Apr 9, 2025 by Twi-etn
[Usage] llava-1.6-34在推理图像上输出不符合要求
#1862 opened Apr 1, 2025 by july-love
[Usage] ImportError: cannot import name 'KeywordsStoppingCriteria' from 'llava.model.utils'
#1861 opened Mar 25, 2025 by kky677
如何解决UserWarning: do_sample is set to False. However, temperature is set to 0.0 -- this flag is only used in sample-based generation modes.
#1859 opened Mar 24, 2025 by july-love
[Question] ValueError: The train_dataset does not implement __len__, max_steps has to be specified. The number of steps needs to be known in advance for the learning rate scheduler.
#1858 opened Mar 21, 2025 by UCASlemontea
1
[Question] can not find the script extract_video_frames.py
#1857 opened Mar 20, 2025 by ge-bin-hui
[Question] 维度不匹配
#1856 opened Mar 18, 2025 by CurryaNa
IndexError: piece id is out of range.
#1854 opened Mar 17, 2025 by kydxh
Proposal: Integrating Sparse Autoencoders (SAEs) for LLaVA Interpretability
#1852 opened Mar 16, 2025 by jmanhype
[Feature request]
#1851 opened Mar 14, 2025 by DAIDJACREX
Question about the shape of lm_head.weight
#1850 opened Mar 12, 2025 by Jay-zzcoder
[Usage] from .model.language_model.llava_llama import LlavaLlamaForCausalLM is not work
#1849 opened Mar 10, 2025 by GoodStarLink
1
[Usage] Couldn't save full model after pretrain.
#1848 opened Mar 9, 2025 by keanshi-nlp
ProTip! Add no:assignee to see everything that’s not assigned.