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

288 Open 5,692 Closed
288 Open 5,692 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

基于最新的LLaMA-Factory训练Qwen2.5-vl, 训练变得非常慢 bug Something isn't working pending This problem is yet to be addressed
#7030 opened Feb 21, 2025 by leon-cas
1 task done
deepseek r1微调 enhancement New feature or request pending This problem is yet to be addressed
#7027 opened Feb 21, 2025 by ZTurboX
1 task done
5
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xc0 in position 17: invalid start byte bug Something isn't working pending This problem is yet to be addressed
#7016 opened Feb 20, 2025 by DspringL
1 task done
使用昇腾910A llama factory sft qwen2-7b时报错E40024: 2025-02-20-14:05:46.947.014 Failed call Python Func/Meathod [get_binfile_sha256_hash_from_c], bug Something isn't working npu This problem is related to NPU devices pending This problem is yet to be addressed
#7014 opened Feb 20, 2025 by Goo-goo-goo
1 task done
在服务器端配置端口映射后，WebUI无法正常显示。确实前端css文件 bug Something isn't working pending This problem is yet to be addressed
#7013 opened Feb 20, 2025 by HemiFate
1 task done
使用API模型能力变差 bug Something isn't working pending This problem is yet to be addressed
#7010 opened Feb 20, 2025 by zzysos
1 task done
3
mac本用llama-factory如何用MPS ？ enhancement New feature or request pending This problem is yet to be addressed
#7001 opened Feb 19, 2025 by catman002
1 task done
A800 7*80g 全参微调qwen-2.5-32b OOM？ bug Something isn't working pending This problem is yet to be addressed
#6999 opened Feb 19, 2025 by coinfist-lucian
1 task done
6
启动WebUI失败 bug Something isn't working pending This problem is yet to be addressed
#6989 opened Feb 18, 2025 by xfrqh
1 task done
4
minicpm_2_6o全量微调验证集eval_loss不计算不打印，也不绘制eval_loss图 bug Something isn't working pending This problem is yet to be addressed
#6988 opened Feb 18, 2025 by Maflyflyy
1 task done
1
[help]如何添加规则到数据集的每个条目中，并且不影响返回值 bug Something isn't working pending This problem is yet to be addressed
#6984 opened Feb 18, 2025 by frankyuan
1 task done
怎么返回输出token的prob呢? enhancement New feature or request pending This problem is yet to be addressed
#6980 opened Feb 18, 2025 by PapaMadeleine2022
1 task done
converting model Error: unknown data type: I32 bug Something isn't working pending This problem is yet to be addressed
#6971 opened Feb 17, 2025 by nemoisfash
1 task done
用deepspeed zero-3-offload去微调DeepSeek-R1-Distill-Qwen-32B，系统卡住，长时间无反应 bug Something isn't working pending This problem is yet to be addressed
#6964 opened Feb 17, 2025 by erichuazhou
1 task done
3
[HELP] Runable solution of RTX 5090 GPU + Linux Driver version + Pytorch version + Deepspeed version for LLM finetuning bug Something isn't working pending This problem is yet to be addressed
#6958 opened Feb 17, 2025 by 0781532
1 task done
2
单机多卡 resume_from_checkpoint 时报错 assert len(self.ckpt_list) > 0 bug Something isn't working pending This problem is yet to be addressed
#6955 opened Feb 16, 2025 by Cassieyy
1 task done
9
Error in the process of fine-tuning qwen2.5vl-7b evaluate&predict data = [self.dataset[idx] for idx in possibly_batched_index] KeyError: 0 bug Something isn't working pending This problem is yet to be addressed
#6947 opened Feb 14, 2025 by illusionnnnnnn
1 task done
11
使用unsloth报错 bug Something isn't working pending This problem is yet to be addressed
#6945 opened Feb 14, 2025 by Harris-Xie
1 task done
Training Qwen/Qwen2.5-Coder-32B-Instruct model OOM bug Something isn't working pending This problem is yet to be addressed
#6942 opened Feb 14, 2025 by mertunsall
1 task done
3
rm lora训练完成后，执行export合并后结果模型并不是一个reward model。 bug Something isn't working pending This problem is yet to be addressed
#6934 opened Feb 14, 2025 by yangyang6666
1 task done
1
安装完成后执行 llamafactory-cli -v 报 fatal error: stdlib.h: No such file or directory #include_next <stdlib.h>，CentOS7 bug Something isn't working pending This problem is yet to be addressed
#6932 opened Feb 14, 2025 by lunza
1 task done
0.9.2版本训练deepseek3问题 bug Something isn't working pending This problem is yet to be addressed
#6923 opened Feb 13, 2025 by TexasRangers86
1 task done
failed to docker build bug Something isn't working pending This problem is yet to be addressed
#6922 opened Feb 13, 2025 by Danee-wawawa
1 task done
希望支持 Tencent-Hunyuan-7B enhancement New feature or request pending This problem is yet to be addressed
#6919 opened Feb 12, 2025 by xenv
1 task done
Qwen2.5-VL-7B-Instruct推理bug：RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cuda:1! bug Something isn't working pending This problem is yet to be addressed
#6910 opened Feb 12, 2025 by Felixvillas
1 task done
11
ProTip! Updated in the last three days: updated:>2025-02-18.