Skip to content

Issues: hiyouga/LLaMA-Factory

🚨FAQs | 常见问题🚨
#4614 opened Jun 28, 2024 by hiyouga
Open
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

270 Open 5,578 Closed
270 Open 5,578 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

Use multipage and sidebar components in the web app enhancement New feature or request pending This problem is yet to be addressed
#6841 opened Feb 6, 2025 by yvrjsharma
1 task done
RuntimeError: Error(s) in loading state_dict for PeftModelForCausalLM bug Something isn't working pending This problem is yet to be addressed
#6840 opened Feb 6, 2025 by xzq11111
1 task done
ValueError: len(videos) is less than the number of <video> tokens. bug Something isn't working pending This problem is yet to be addressed
#6839 opened Feb 6, 2025 by MengHao666
1 task done
Dimension out of range bug Something isn't working pending This problem is yet to be addressed
#6838 opened Feb 6, 2025 by poo0054
1 task done
1
llamafactory最新版0.9.2.dev0，unsloth加速训练报错 bug Something isn't working pending This problem is yet to be addressed
#6836 opened Feb 6, 2025 by yecphaha
1 task done
DeepSeek-R1-Distill-Qwen SFT训练问题 bug Something isn't working pending This problem is yet to be addressed
#6833 opened Feb 6, 2025 by TW-NLP
1 task done
4
qwen2.5-72B-Instruct训练一半数据卡住 bug Something isn't working pending This problem is yet to be addressed
#6832 opened Feb 6, 2025 by CuiXinYu123
1 task done
请问有deepseek v3或r1微调的例子吗 bug Something isn't working pending This problem is yet to be addressed
#6829 opened Feb 6, 2025 by glowwormX
1 task done
3
8卡h20，cutoff_len超过1000就报错 bug Something isn't working pending This problem is yet to be addressed
#6828 opened Feb 6, 2025 by j-river
1 task done
CUDA OOM in the middle of QLoRA with Llama 3.3 70B 4-bit AWQ bug Something isn't working pending This problem is yet to be addressed
#6827 opened Feb 5, 2025 by paolovic
1 task done
求助：如何对 DeepSeek R1 进行 SFT bug Something isn't working pending This problem is yet to be addressed
#6824 opened Feb 5, 2025 by yuchunyu97
1 task done
1
504 Gateway Time-out bug Something isn't working pending This problem is yet to be addressed
#6822 opened Feb 5, 2025 by MarkJiang-maji
1 task done
全量训练MiniCPM-o问题 bug Something isn't working pending This problem is yet to be addressed
#6819 opened Feb 5, 2025 by JACKYLUO1991
1 task done
5
NPU ds3_ofld训练不释放内存最终OOM bug Something isn't working npu This problem is related to NPU devices pending This problem is yet to be addressed
#6816 opened Feb 5, 2025 by ultramangod
1 task done
Do you support Mamba-Codestral-7B? enhancement New feature or request pending This problem is yet to be addressed
#6808 opened Feb 4, 2025 by displaywz
1 task done
lora微调minicpm-o-2.6 卡着不动，A6000 48G * 8卡，batchsize = 1，但是单卡又可以微调，拉的最新的代码，看issuse很多出现这个问题但都没解决，qwen2vl 多卡微调没有卡死 bug Something isn't working pending This problem is yet to be addressed
#6806 opened Feb 4, 2025 by cqray1990
1 task done
微调Qwen2.5-VL 7B过程中显存会增加导致OOM，Qwen2-VL 7B则不会 bug Something isn't working pending This problem is yet to be addressed
#6804 opened Feb 4, 2025 by missTL
1 task done
1
结合 GRPO 支持 DeepSeek-R1 等推理模型的复现，达到 huggingface open-r1 的类似效果 enhancement New feature or request pending This problem is yet to be addressed
#6792 opened Feb 2, 2025 by submartingales
1 task done
8
Qwen2.5-VL full sft dtype error bug Something isn't working pending This problem is yet to be addressed
#6791 opened Feb 2, 2025 by wyuc
1 task done
1
ValueError: The checkpoint you are trying to load has model type llava_mistral 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. bug Something isn't working pending This problem is yet to be addressed
#6781 opened Jan 30, 2025 by dainini
1 task done
有计划支持Deepseek的janus pro微调么 enhancement New feature or request pending This problem is yet to be addressed
#6775 opened Jan 28, 2025 by mkygogo
1 task done
2
Q_APOLLO? enhancement New feature or request pending This problem is yet to be addressed
#6774 opened Jan 28, 2025 by inflatebot
1 task done
希望支持RFT微调方法。 enhancement New feature or request pending This problem is yet to be addressed
#6763 opened Jan 26, 2025 by bhnan
1 task done
One of the subprocesses has abruptly died during map operation.To debug the error, disable multiprocessing. 无论numworkers多大都没用 bug Something isn't working pending This problem is yet to be addressed
#6762 opened Jan 25, 2025 by miaowuawa
1 task done
1
does save_strategy conflicts with save_total_limit? bug Something isn't working pending This problem is yet to be addressed
#6761 opened Jan 25, 2025 by VoiceBeer
1 task done
3
ProTip! Updated in the last three days: updated:>2025-02-03.