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

317 Open 5,720 Closed
317 Open 5,720 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

<think>标签训练后，模型预测结果无<think>标签 bug Something isn't working pending This problem is yet to be addressed
#7119 opened Feb 28, 2025 by qubingxin
1 task done
2
模型微调参数优化 duplicate This issue or pull request already exists
#7111 opened Feb 28, 2025 by hackerhaiJu
1 task done
显存分配不平衡 bug Something isn't working pending This problem is yet to be addressed
#7110 opened Feb 28, 2025 by Kyrie666
1 task done
2
微调deepseek R1-7b保存后，推理乱码 bug Something isn't working pending This problem is yet to be addressed
#7109 opened Feb 28, 2025 by JYaooo
1 task done
2
After training the phi3 model, export error bug Something isn't working pending This problem is yet to be addressed
#7107 opened Feb 28, 2025 by sanqiuli
1 task done
1
support Moonlight's Muon enhancement New feature or request pending This problem is yet to be addressed
#7105 opened Feb 28, 2025 by bigcash
1 task done
llama3-llava-next-8b 全参微调报错 bug Something isn't working pending This problem is yet to be addressed
#7102 opened Feb 27, 2025 by liboaccn
1 task done
3
增大图片分辨率到原始qwen2.5 的 3584 *3584，为什么多机多卡（64卡）会爆显存 bug Something isn't working pending This problem is yet to be addressed
#7099 opened Feb 27, 2025 by WYRTDCQ
1 task done
Triton Autotune Directory Exists but "No Such File or Directory" Error Appears bug Something isn't working pending This problem is yet to be addressed
#7097 opened Feb 27, 2025 by MayurKuchhadiya
1 task done
1
访问服务器部署的webUI一直卡在加载 bug Something isn't working pending This problem is yet to be addressed
#7095 opened Feb 27, 2025 by Tattoo-hy
1 task done
Support Phi-4-mini and Phi-4-multimodal enhancement New feature or request pending This problem is yet to be addressed
#7093 opened Feb 27, 2025 by liukangxu
1 task done
pt stage set eval_dataset doesn't work bug Something isn't working pending This problem is yet to be addressed
#7092 opened Feb 27, 2025 by xiadingZ
1 task done
1
On the Ascend platform, does adding" --flash_attn True "have any effect for training speed? bug Something isn't working npu This problem is related to NPU devices pending This problem is yet to be addressed
#7090 opened Feb 27, 2025 by Lexlum
1 task done
1
Error splitting the input into NAL units. bug Something isn't working pending This problem is yet to be addressed
#7087 opened Feb 26, 2025 by MengHao666
1 task done
Bug when use multuple gpus on ray bug Something isn't working pending This problem is yet to be addressed
#7084 opened Feb 26, 2025 by oasis-0927
1 task done
1
minicpi-o-2.6 fitunue bug Something isn't working pending This problem is yet to be addressed
#7082 opened Feb 26, 2025 by zll0000
1 task done
@BUAADreamer
3
special token未能输出 solved This problem has been already solved
#7080 opened Feb 26, 2025 by katouHui
1 task done
6
vllm infer not support Qwen2audio bug Something isn't working pending This problem is yet to be addressed
#7078 opened Feb 26, 2025 by WWWWWLI
1 task done
2
支持qwen2-audio的dpo微调吗？ solved This problem has been already solved
#7072 opened Feb 26, 2025 by cy565025164
1 task done
5
使用deepspeed进行2机8卡训练时，怎么把模型切成16份呢？我发现现在只会切成8份。 bug Something isn't working pending This problem is yet to be addressed
#7066 opened Feb 25, 2025 by joyyyhuang
1 task done
3
关于FunctionFormatter中think标签的疑问 bug Something isn't working pending This problem is yet to be addressed
#7064 opened Feb 25, 2025 by zhangch-ss
1 task done
1
Problems arising from Inferrence bug Something isn't working pending This problem is yet to be addressed
#7062 opened Feb 25, 2025 by yaosheng-zhang
1 task done
2
多卡微调Qwen2.5-14B显存分配不均 bug Something isn't working pending This problem is yet to be addressed
#7055 opened Feb 24, 2025 by Jimmy-L99
1 task done
2
使用streaming模式，但内存随着训练会增加，符合预期吗？ bug Something isn't working pending This problem is yet to be addressed
#7049 opened Feb 24, 2025 by caoxu915683474
1 task done
Dataset image path incorrectly loaded 多模态数据集图像路径错误 bug Something isn't working pending This problem is yet to be addressed
#7046 opened Feb 24, 2025 by SovietLongbow
1 task done
ProTip! no:milestone will show everything without a milestone.