Skip to content

Issues: PKU-YuanGroup/MoE-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

Clear current search query, filters, and sorts
62 Open 33 Closed
62 Open 33 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

Support cuda 12
#37 opened Feb 12, 2024 by fishfree
1
is support video ?
#15 opened Feb 2, 2024 by awzhgw
3
ERROR: Could not build wheels for flash-attn, which is required to install pyproject.toml-based projects
#19 opened Feb 3, 2024 by andysingal
2
languageBindVideo model may be hang ?
#21 opened Feb 3, 2024 by awzhgw
8
Wrong cuda allocation
#23 opened Feb 4, 2024 by paulgavrikov
5
Whether stage-2 pre-train model(llavaphi-2.7b-finetune) is released?
#24 opened Feb 5, 2024 by yucheng-zyc
4
MoE-LLaVA-StableLM for 4-bits and 8-bit
#30 opened Feb 7, 2024 by NikiBase
1
第二阶段，loss下降到多少比较合理？
#31 opened Feb 7, 2024 by awzhgw
1
License Questions
#32 opened Feb 8, 2024 by kbrostrom
1
Can i use this to detect events in the video???
#33 opened Feb 9, 2024 by Shekharmeena28
1
finetune阶段内存占用太高
#34 opened Feb 9, 2024 by awzhgw
2
Wrong depedancies, why deepspeed dependency for inference, better transformers integration
#35 opened Feb 10, 2024 by sujitvasanth
3
Is llavallama moe supported?
#9 opened Feb 1, 2024 by DietDietDiet
14
Eval on MMVET
#36 opened Feb 10, 2024 by BeachWang
1
inference error in llavamistral
#38 opened Feb 13, 2024 by saeedkhaki92
2
Inference without Deepspeed
#40 opened Feb 19, 2024 by aaronnat23
1
用LLava官方脚本替换Qwen2，用mpt的template训练 loss 0
#42 opened Feb 20, 2024 by lucasjinreal
26
[Discussion] How to improve model's understanding of high-resolution images？
#46 opened Feb 23, 2024 by whalefa1I
1
推理效率对比问题
#47 opened Feb 23, 2024 by aprilehannibal
1
Error during training on custom dataset
#48 opened Feb 23, 2024 by saeedkhaki92
1
[Question] About nlp_tune data.
#49 opened Feb 26, 2024 by Lucky-Lance
2
[Question] Scale down futher to support IOT usecases?
#50 opened Feb 28, 2024 by kinchahoy
1
[Usage] ValueError: Unknown image tower: /data1/ljq/Moellava/MoE-LLaVA-Qwen-1.8B-4e/clip-vit-large-patch14-336
#51 opened Feb 28, 2024 by xiangchihuoguo
3
[Question] How to finetune the moe-llava model on customized data?
#52 opened Feb 29, 2024 by RayshenSL
[Question] How to export the MoE to onnx
#99 opened Mar 10, 2025 by AdilAdam
1
ProTip! Exclude everything labeled bug with -label:bug.