Skip to content

Issues: hiyouga/LLaMA-Factory

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

430 Open 6,120 Closed
430 Open 6,120 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

为什么deepspeed配置文件有zero0,zero2,zero3，没有zero1 bug Something isn't working pending This problem is yet to be addressed
#7853 opened Apr 25, 2025 by hellostronger
1 task done
How to get LLM's embedding during batch inference? enhancement New feature or request pending This problem is yet to be addressed
#7851 opened Apr 25, 2025 by importrayhan
1 task done
Qwen2-VL在grounding任务微调后输出异常终止 bug Something isn't working pending This problem is yet to be addressed
#7850 opened Apr 25, 2025 by RunkunL
1 task done
适应Lora对QWQ推理模型进行微调以后回答效果很差 bug Something isn't working pending This problem is yet to be addressed
#7849 opened Apr 25, 2025 by want-well
1 task done
v0.9.2 - QWen fine-tuned, GGUF for LM Studio: error loading model: missing tensor 'token_embd.weight' bug Something isn't working pending This problem is yet to be addressed
#7848 opened Apr 25, 2025 by SINAPSA-IC
1 task done
文档有小错误 bug Something isn't working pending This problem is yet to be addressed
#7846 opened Apr 25, 2025 by sisrfeng
1 task done
1
Kimi-VL-A3B-Instruct train的时候，train的进度不动，但显卡在运行 bug Something isn't working pending This problem is yet to be addressed
#7845 opened Apr 25, 2025 by luojingbao
1 task done
@Kuangdd01
5
H20多卡训练batch大于1学习率一直为0 bug Something isn't working pending This problem is yet to be addressed
#7839 opened Apr 24, 2025 by artless-spirit
1 task done
1
单机多卡8快h20训练，卡住了没有报错。 bug Something isn't working pending This problem is yet to be addressed
#7836 opened Apr 24, 2025 by pureloveljc
1 task done
2
单机连续实验wandb的run_name会覆盖掉 bug Something isn't working pending This problem is yet to be addressed
#7835 opened Apr 24, 2025 by dbcSep03
1 task done
官方推荐的cuda12.2没有pytorch版本适配 bug Something isn't working pending This problem is yet to be addressed
#7834 opened Apr 24, 2025 by YoLung
1 task done
CUDA out of memory when training DPO in parallel on multiple GPUs bug Something isn't working pending This problem is yet to be addressed
#7833 opened Apr 24, 2025 by zhengyangyong
1 task done
5
RuntimeError: CUDA driver error: invalid argument bug Something isn't working pending This problem is yet to be addressed
#7832 opened Apr 24, 2025 by FloSophorae
1 task done
5
在保存in _save_checkpoint 的时候，提示metric_value = metrics[metric_to_check] KeyError: 'eval_loss'，如何解决。 bug Something isn't working pending This problem is yet to be addressed
#7816 opened Apr 22, 2025 by Kb519
1 task done
1
DPO显存分布不均匀 bug Something isn't working pending This problem is yet to be addressed
#7815 opened Apr 22, 2025 by Arcmoon-Hu
1 task done
Support for images_root field for multimodal training data solved This problem has been already solved
#7814 opened Apr 22, 2025 by tianbinli
1 task done
3
qwen2vl reward model 如何离线推理啊 bug Something isn't working pending This problem is yet to be addressed
#7809 opened Apr 22, 2025 by minmummax
1 task done
vllm推理结果不一致(temperature = 0,seed=42) bug Something isn't working pending This problem is yet to be addressed
#7807 opened Apr 22, 2025 by gnodez
1 task done
3
使用最新master 分支训练DeepSeek V3训练，设置DeepseekV3MoE为叶子结点报错 bug Something isn't working pending This problem is yet to be addressed
#7800 opened Apr 22, 2025 by Han-Huaqiao
1 task done
1
是否可以支持更长训练的训练，比如150K+的一些训练方法？ solved This problem has been already solved
#7790 opened Apr 21, 2025 by h123fire
1 task done
3
🚨 Bug: 使用 vLLM 推理后端时 n 参数无效，始终为 1 bug Something isn't working pending This problem is yet to be addressed
#7782 opened Apr 20, 2025 by Curious-chen
1 task done
GH200 ARM support bug Something isn't working pending This problem is yet to be addressed
#7780 opened Apr 20, 2025 by berkeleyljj
1 task done
qlora微调Qwen2.5-Omni模型报错ValueError: Processor was not found, please check and update your processor config. bug Something isn't working pending This problem is yet to be addressed
#7778 opened Apr 20, 2025 by leidaoyu
1 task done
4
Runtime error, invalid examples bug Something isn't working pending This problem is yet to be addressed
#7777 opened Apr 19, 2025 by berkeleyljj
1 task done
2
Is it possible to support microsoft/bitnet-b1.58-2B-4T ? enhancement New feature or request pending This problem is yet to be addressed
#7775 opened Apr 19, 2025 by hbj52152
1 task done
ProTip! Exclude everything labeled bug with -label:bug.