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

RuntimeError: expected mat1 and mat2 to have the same dtype, but got: float != c 10::BFloat16
#772 opened Jun 15, 2024 by Yanllan updated Jun 15, 2024
"<image>" is absent in "llava_instruct_150k_zh.jsonl"
#771 opened Jun 15, 2024 by wusize updated Jun 15, 2024
Citation for OpenRLHF in relation to the XTuner RLHF code and architecture
#770 opened Jun 14, 2024 by hijkzzz updated Jun 15, 2024
1
请问是否计划支持Qwen2-128K的训练？
#755 opened Jun 8, 2024 by scewiner updated Jun 14, 2024
3
多卡微调 llava 时 数据集加载卡死
#768 opened Jun 14, 2024 by wutaiqiang updated Jun 14, 2024
2
关于qwen1.5长序列训练的疑问
#761 opened Jun 11, 2024 by macheng6 updated Jun 14, 2024
4
trust_remote_code=True不起作用
#767 opened Jun 14, 2024 by macheng6 updated Jun 14, 2024
How to perform validation during the fine-tune training process on llava_llama3_8b_instruct_full_clip_vit_large_p14_336_lora_e1_gpu8_finetune?
#749 opened Jun 6, 2024 by J0eky updated Jun 12, 2024
2
[Bug] Map with add_length will cause memory OOM
#758 opened Jun 10, 2024 by tonysy updated Jun 12, 2024
@HIT-cwh
3
bug
#762 opened Jun 12, 2024 by laozhai507 updated Jun 12, 2024
xtuner 是否支持自动的loss function
#753 opened Jun 7, 2024 by Jason8Kang updated Jun 11, 2024
4
Convert .pth of lava-phi3-lora failed
#745 opened Jun 4, 2024 by xsx1001 updated Jun 11, 2024
3
LengthGroupedSampler 根据length排序是必要的吗？
#756 opened Jun 9, 2024 by shockjiang updated Jun 11, 2024
1
关于qwen1.5+deepspeed_zero3+序列并行保存模型文件的问题
#746 opened Jun 4, 2024 by macheng6 updated Jun 11, 2024
2
llava-phi3-mini conversion to gguf format
#759 opened Jun 10, 2024 by nakoeni updated Jun 10, 2024
Errors of llava pretrain for phi3_mini_4k_instruct_clip_vit_large_p14_336
#713 opened May 23, 2024 by JiamingLv updated Jun 7, 2024
3
ValueError: The checkpoint you are trying to load has model type llava_llama but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.
#748 opened Jun 5, 2024 by ztfmars updated Jun 7, 2024
1
The sequence parallel is open when I don't use it.
#669 opened May 9, 2024 by amulil updated Jun 7, 2024
@HIT-cwh
4
ImportError: Failed to import AutoModelForCausalLM from xtuner.model.transformers_models in None
#740 opened Jun 2, 2024 by ldh127 updated Jun 5, 2024
12
如何将xtuner微调得到的llava模型转换成lmdeploy可部署的格式
#742 opened Jun 3, 2024 by rivhea updated Jun 3, 2024
TypeError: object of type 'NoneType' has no len()
#741 opened Jun 3, 2024 by puffanddmx updated Jun 3, 2024
使用自己的数据集训练时报错
#734 opened May 30, 2024 by cococoda updated Jun 1, 2024
2
what does this mean
#739 opened Jun 1, 2024 by jackylee1 updated Jun 1, 2024
openELM pre-train weights
#738 opened Jun 1, 2024 by shockjiang updated Jun 1, 2024
执行 NPROC_PER_NODE=2 xtuner train /root/StableDiffusionGPT/config/internlm2_1_8b_qlora_alpaca_e3_copy.py --work-dir /root/test/ft/train --deepspeed deepspeed_zero2 指令运行报错
#719 opened May 26, 2024 by LTtt456c updated May 30, 2024
2
ProTip! Mix and match filters to narrow down what you’re looking for.