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

54 Open 267 Closed
54 Open 267 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

求助max_epochs 的问题
#677 opened May 11, 2024 by Franklin-L
warning on CUTLASS&sparse_attn&triton
#676 opened May 11, 2024 by shockjiang
xtuner mmbench on xtuner/ lava-Llama 3-8b-v1_1-hf
#673 opened May 10, 2024 by Yanllan
1
Add a feature to merge the PTH format with the original LLM directly. feature request
#670 opened May 9, 2024 by LiyanJin
The sequence parallel is open when I don't use it.
#669 opened May 9, 2024 by amulil
@HIT-cwh
2
支持自定义视觉编码器么（llava-llama3）?
#668 opened May 9, 2024 by Yanllan
1
How to solve the following problem with xtuner on Slurm？
#667 opened May 9, 2024 by har77774
1
llava-llama3-8b llm+llm adapter merge error
#662 opened May 8, 2024 by ztfmars
2
关于微调
#660 opened May 8, 2024 by Toblame
llava-surgery.py for phi3_mini to get gguf
#659 opened May 7, 2024 by rezacopol
1
PROMPT_TEMPLATE.llama2_chat效果下降
#658 opened May 7, 2024 by dongjiancheng77
@HIT-cwh
7
FSDP的训练有两种错误，不确定是什么原因，代码基本上是例子中的代码
#657 opened May 7, 2024 by apachemycat
failed to convert convert llava-llama3 model to hf format
#656 opened May 7, 2024 by Jason8Kang
@LZHgrla
9
multi image inputs supports for xtuner chat in llava-llama3?
#655 opened May 7, 2024 by ztfmars
1
请问有支持PoSE的打算吗？ feature request
#644 opened May 6, 2024 by 2793145003
xtuner训练 InternLM 1.8B模型报错 assert position_ids is not None and (position_ids.max() + 1) >= kv_seq_len
#643 opened May 6, 2024 by apachemycat
@HIT-cwh
1
convert_xtuner_weights_to_llava.py and convert_xtuner_weights_to_hf.py can support llava-next model?
#642 opened May 4, 2024 by awzhgw
2
llava-phi3 模型转换到llava模型报错。求助，怎么解决？
#641 opened May 4, 2024 by awzhgw
@pppppM
1
ChatGLM3-6b测试模型时报错AttributeError: can't set attribute
#636 opened May 1, 2024 by padsasdasd
@LZHgrla
1
计划支持多模态模型，比如llava1.5的long sequence的训练吗
#629 opened Apr 30, 2024 by dyyoungg
7
【Program hangs with no output.】
#626 opened Apr 28, 2024 by Luo-Z13
@LZHgrla
11
使用官方的chat对话时, 结尾总是会跟上<|eot_id|>, 不知道是什么原因.
#620 opened Apr 26, 2024 by tian969
@hhaAndroid
5
是否会支持：llava 1.6+llama3 8B的模型呢？
#604 opened Apr 24, 2024 by awzhgw
3
是否会支持：llava 1.6+llama3 70B的模型呢？
#601 opened Apr 23, 2024 by awzhgw
3
support InternVL1.5 feature request
#599 opened Apr 23, 2024 by choyakawa
ProTip! Adding no:label will show everything without a label.