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

415 Open 5,967 Closed
415 Open 5,967 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

Tuned Model's processor can't tokenize my text input properly. bug Something isn't working pending This problem is yet to be addressed
#7608 opened Apr 5, 2025 by miko8422
1 task done
1
Model Integration Pipeline enhancement New feature or request pending This problem is yet to be addressed
#7607 opened Apr 4, 2025 by WeizhenWang-1210
1 task done
1
单机多卡预训练BUG bug Something isn't working pending This problem is yet to be addressed
#7604 opened Apr 4, 2025 by zhangtianhong-1998
1 task done
fine-tuning on the video sample dataset gives weird output bug Something isn't working pending This problem is yet to be addressed
#7602 opened Apr 4, 2025 by lis-kp
1 task done
1
SwanLabCallback isn't initialized correctly when transformers==4.50.0 bug Something isn't working pending This problem is yet to be addressed
#7600 opened Apr 4, 2025 by Luffy-ZY-Wang
1 task done
2
Expose Ray's Runtime Environment enhancement New feature or request pending This problem is yet to be addressed
#7598 opened Apr 3, 2025 by ssmall41
1 task done
2
Grounding sft is needed enhancement New feature or request pending This problem is yet to be addressed
#7586 opened Apr 3, 2025 by evenboos
1 task done
单机双卡A100 40G训练gemma3-27b lora非常慢 bug Something isn't working pending This problem is yet to be addressed
#7584 opened Apr 3, 2025 by hanggun
1 task done
2
未来会支持混合图文数据的多模态增量预训练吗？ enhancement New feature or request pending This problem is yet to be addressed
#7581 opened Apr 3, 2025 by windn0
1 task done
更新项目后公开基准mmlu等测试结果不同 bug Something isn't working pending This problem is yet to be addressed
#7575 opened Apr 2, 2025 by xiao-liya
1 task done
ascend-npu，执行模型评估脚本时，出现IndexError: list index out of range bug Something isn't working npu This problem is related to NPU devices pending This problem is yet to be addressed
#7574 opened Apr 2, 2025 by doit-5618
1 task done
sft阶段使用streaming dataset和do_predict时报错 bug Something isn't working pending This problem is yet to be addressed
#7571 opened Apr 2, 2025 by xxchauncey
1 task done
在使用webui时，初始loss图片无法加载，需要刷新才能加载 bug Something isn't working pending This problem is yet to be addressed
#7561 opened Apr 1, 2025 by HemiFate
1 task done
如何创建评测数据集 enhancement New feature or request pending This problem is yet to be addressed
#7549 opened Mar 31, 2025 by 1212wuhu
1 task done
Problem with LLama3.3-70b-Instruct PPO+qlora bug Something isn't working pending This problem is yet to be addressed
#7544 opened Mar 31, 2025 by ChengwZhou
1 task done
1
PPO training - raise ValueError("resume_from_checkpoint will be supported in the future version.") enhancement New feature or request pending This problem is yet to be addressed
#7538 opened Mar 30, 2025 by Jinstorm
1 task done
Mac M4 support enhancement New feature or request pending This problem is yet to be addressed
#7534 opened Mar 30, 2025 by rogermayo182
1 task done
使用DPO Lora微调Qwen25 VL，loss为nan bug Something isn't working pending This problem is yet to be addressed
#7531 opened Mar 29, 2025 by stillbetter
1 task done
3
gemma3 multimodal finetuning: vision config not being properly initialized bug Something isn't working pending This problem is yet to be addressed
#7529 opened Mar 29, 2025 by imamitsingh
昇腾910 32G 8卡，微调DeepSeek-R1-Distill-Qwen-14B，设置cutoff_len: 8192，启动deepspeed z3 offload，还是报错OOM bug Something isn't working npu This problem is related to NPU devices pending This problem is yet to be addressed
#7528 opened Mar 29, 2025 by qyy85
1 task done
2
在升腾npu-310p上能运行启动api，但是显存占用对比英伟达翻倍了 bug Something isn't working npu This problem is related to NPU devices pending This problem is yet to be addressed
#7522 opened Mar 28, 2025 by monument-and-sea-all-the-gift
1 task done
3
Why rebase the repository and push it with --force? bug Something isn't working pending This problem is yet to be addressed
#7518 opened Mar 28, 2025 by Snowdar
1 task done
使用vllm_infer一次性推理多个样本会报错 bug Something isn't working pending This problem is yet to be addressed
#7513 opened Mar 27, 2025 by DotWang
1 task done
1
使用70G的数据训练模型，在tokenizer阶段异常退出 bug Something isn't working pending This problem is yet to be addressed
#7510 opened Mar 27, 2025 by Miracle1991
1 task done
3
最新版本如何正确使用验证集？How to eval in latest version? bug Something isn't working pending This problem is yet to be addressed
#7502 opened Mar 27, 2025 by Moon-404
1 task done
2
ProTip! Follow long discussions with comments:>50.