Skip to content

Issues: InternLM/xtuner

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
92 Open 299 Closed
92 Open 299 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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

CUDA out of memory gpu memory
#88 opened Sep 1, 2023 by RickMeow updated Oct 31, 2023
@LZHgrla
5
About RLHF need feature request good first issue Good for newcomers
#93 opened Sep 4, 2023 by xiaohangguo updated Dec 14, 2023
@pppppM
3
报名参加书生·浦语大模型实战营——两周带你玩转微调部署评测全链路
#282 opened Dec 26, 2023 by vansin updated Dec 28, 2023
3
DPO dataset format and loss
#344 opened Jan 20, 2024 by samedii updated Jan 22, 2024
1
Any plans to support Gradio for local web demos? feature request
#301 opened Jan 10, 2024 by KooSung updated Feb 1, 2024
1
RLHF and DPO feature request
#415 opened Feb 15, 2024 by rese1f updated Feb 18, 2024
RuntimeError: Rank 2 successfully reached monitoredBarrier, but received errors while waiting for send/recv from rank 0. Please check rank 0 logs for faulty rank.
#457 opened Mar 9, 2024 by lesjie-wen updated Mar 11, 2024
2
请问如何对deepspeed中的相关参数进行配置，比如master_port？ enhancement New feature or request
#467 opened Mar 12, 2024 by GolfHotelSierra updated Mar 12, 2024
2
Is there any plan to support MAC? feature request good first issue Good for newcomers
#461 opened Mar 11, 2024 by jacky68147527 updated Mar 12, 2024
xtuner check-custom-dataset /home/internlm2.py不通过怎么办？
#469 opened Mar 12, 2024 by SaltedFishBot updated Mar 13, 2024
@HIT-cwh
1
[Feature] 提前确认离线处理的 llava 数据所使用的 tokenizer 是否和当前配置中一致
#484 opened Mar 15, 2024 by hhaAndroid updated Mar 15, 2024
TypeError: LlamaRotaryEmbedding.forward() missing 1 required positional argument: 'position_ids'
#491 opened Mar 19, 2024 by LZHgrla updated Mar 19, 2024
1
FEAT / Optim: Add Freeze FT and GaLore optimizer feature request
#498 opened Mar 20, 2024 by xxll88 updated Mar 22, 2024
InternLM2_Chat模型工具调用能力微调是否有相关样例？
#403 opened Feb 5, 2024 by klykq111 updated Mar 25, 2024
3
[Feature] Any plans to add support for video LLMs? feature request
#499 opened Mar 20, 2024 by yeliudev updated Mar 26, 2024
2
TypeError: scaled_dot_product_attention() got an unexpected keyword argument 'training' in <xtuner.engine.hooks.evaluate_chat_hook.EvaluateChatHook object at 0x7f1ce9adfe20>
#515 opened Mar 25, 2024 by QB-Chen updated Mar 27, 2024
1
InternLM一代的微调配置Internlm_chat_20b_qlora_oasst1_e3微调Internlm2_chat_20b成功，但是chat时报错
#518 opened Mar 26, 2024 by QB-Chen updated Mar 28, 2024
4
Mixtral 8x7B SFT 问题
#533 opened Mar 29, 2024 by aiyinyuedejustin updated Apr 1, 2024
4
Potential boundary error in utils.py bug Something isn't working
#562 opened Apr 10, 2024 by dongyang2011 updated Apr 11, 2024
1
ModuleNotFoundError: No module named 'mmengine'
#546 opened Apr 8, 2024 by 52THANOS updated Apr 11, 2024
22
请问，会支持video的多模态吗？比如llava-video，minigpt4-video等 feature request
#576 opened Apr 16, 2024 by FDInSky updated Apr 18, 2024
support InternVL1.5 feature request
#599 opened Apr 23, 2024 by choyakawa updated Apr 24, 2024
Support finetuning LLaVA 1.6 feature request
#432 opened Feb 23, 2024 by choyakawa updated Apr 24, 2024
8
是否会支持：llava 1.6+llama3 8B的模型呢？
#604 opened Apr 24, 2024 by awzhgw updated Apr 26, 2024
3
是否可以发布docker，方便快速部署调试 feature request
#593 opened Apr 21, 2024 by DayDreammy updated Apr 29, 2024
ProTip! Find all open issues with in progress development work with linked:pr.