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

211 Open 4,987 Closed
211 Open 4,987 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

reward model 使用do_predict得到的结果和直接用api部署不同 pending This problem is yet to be addressed
#5967 opened Nov 8, 2024 by vxfla
1 task done
冻结vision tower剩下全参数一起DPO训练后推理乱码，如何进行DPO推理 pending This problem is yet to be addressed
#5965 opened Nov 8, 2024 by Sisi0518
微调Qwen2-VL-2B报错 pending This problem is yet to be addressed
#5964 opened Nov 8, 2024 by Liwx1014
1 task done
4
用0.9.0的代码构建镜像，启动容器时出现compatibility mode is UNAVAILABLE pending This problem is yet to be addressed
#5962 opened Nov 8, 2024 by czhcc
1 task done
EETQ.cpython-310-x86_64-linux-gnu.so: undefined symbol: _ZN3c104cuda9SetDeviceEi pending This problem is yet to be addressed
#5960 opened Nov 8, 2024 by hqm19
1 task done
ValueError: This model does not support image input pending This problem is yet to be addressed
#5958 opened Nov 8, 2024 by QichangZheng
1 task done
求助：模型微调时显存足够，预测评估时总是OOM，24G的显存，哪怕微调时只占用了17G，也无法进行预测评估 pending This problem is yet to be addressed
#5957 opened Nov 8, 2024 by qingmeng0906
1 task done
[Help] 关于添加自定义模型训练支持 pending This problem is yet to be addressed
#5951 opened Nov 7, 2024 by amoyplane
1 task done
sft在eval或者predict阶段输出每条样本的log_prob_sum pending This problem is yet to be addressed
#5950 opened Nov 7, 2024 by sc89703312
1 task done
1
请问是否考虑集成trl库的GKD（Generalized Knowledge Distillation Trainer）？ pending This problem is yet to be addressed
#5946 opened Nov 6, 2024 by VincentZ-2020
1 task done
FSDP + lm_head + Liger-Kernel pending This problem is yet to be addressed
#5941 opened Nov 5, 2024 by gotzmann
1 task done
Branch Name in HuggingFace Dataset pending This problem is yet to be addressed
#5940 opened Nov 5, 2024 by mertunsall
1 task done
Export command should export value head for reward modeling stage pending This problem is yet to be addressed
#5939 opened Nov 5, 2024 by amangup
1 task done
Freeze-tuning of LLaVA-NeXT giving IndexError: list index out of range because "image_newline" can't be split using "." pending This problem is yet to be addressed
#5937 opened Nov 5, 2024 by rajats
1 task done
最新版本 trl PPOConfig 不兼容 pending This problem is yet to be addressed
#5936 opened Nov 5, 2024 by techkang
1 task done
when misteral 3B sft will be support？ pending This problem is yet to be addressed
#5935 opened Nov 5, 2024 by alongwithyou
1 task done
SFT后模型合并Lora权重，回答质量下降明显（非Issue #2505，#4913） pending This problem is yet to be addressed
#5930 opened Nov 4, 2024 by BGbigbear
1 task done
1
Use a LoRA finetuned model in Dify? pending This problem is yet to be addressed
#5928 opened Nov 4, 2024 by wingvortex
1 task done
ValueError:This model does not support image input. solved This problem has been already solved
#5918 opened Nov 3, 2024 by zjrwtx
1 task done
7
Hardware Requirement in the readme lacks critical info pending This problem is yet to be addressed
#5916 opened Nov 2, 2024 by xzuyn
llamafactory会考虑支持 Online DPO 吗 pending This problem is yet to be addressed
#5902 opened Nov 1, 2024 by piamo
1 task done
如何添加额外的可训练参数？ pending This problem is yet to be addressed
#5891 opened Nov 1, 2024 by Zheng-Jay
1 task done
与LLaVA官方代码训练结果性能相差较大 pending This problem is yet to be addressed
#5890 opened Nov 1, 2024 by zhipeixu
1 task done
[trainer_utils.py] Why layerwise GaLoRE optimizer does not support gradient accumulation, any underlining reasons? pending This problem is yet to be addressed
#5887 opened Nov 1, 2024 by oncleJules
1 task done
How to mask out specific chunks for loss calculation pending This problem is yet to be addressed
#5886 opened Oct 31, 2024 by Hanzhang-lang
1 task done
1
ProTip! Mix and match filters to narrow down what you’re looking for.