[go: nahoru, domu]
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

Clear current search query, filters, and sorts
63 Open 4,133 Closed
63 Open 4,133 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

Enable Contamination-Free Packaging Method During Pretraining pending This problem is yet to be addressed
#4744 opened Jul 9, 2024 by kostum123 updated Jul 9, 2024
1 task done
使用glaive数据集，实际训练数据中没有obersation的数据并且conversation没有完全参与训练，只有对话前两段参与训练 pending This problem is yet to be addressed
#4729 opened Jul 9, 2024 by tttonytan updated Jul 9, 2024
1 task done
2
Faild to save the gptq quantized weight on Qwen2 72B. pending This problem is yet to be addressed
#4737 opened Jul 9, 2024 by fzp0424 updated Jul 9, 2024
1 task done
2
如果我想把训练后的模型权重由32bit转化为16bit pending This problem is yet to be addressed
#4731 opened Jul 9, 2024 by Suiji12 updated Jul 9, 2024
1 task done
如何将合并后的模型，导出为int4？ pending This problem is yet to be addressed
#4728 opened Jul 9, 2024 by kynow2 updated Jul 9, 2024
1 task done
如果我想把训练后的模型权重由32bit转化为16bit， pending This problem is yet to be addressed
#4719 opened Jul 8, 2024 by Suiji12 updated Jul 8, 2024
1 task done
1
About “RuntimeError: 'weight' must be 2-D” pending This problem is yet to be addressed
#4718 opened Jul 8, 2024 by ldknight updated Jul 8, 2024
1 task done
glm4 deepspeed lora sft : Cannot copy out of meta tensor; no data! pending This problem is yet to be addressed
#4689 opened Jul 5, 2024 by ldknight updated Jul 8, 2024
1 task done
3
怎么实现自建vlm模仿llava进行pt，报错RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn，发现问题在于添加了visual_inputs: true的情况下，stage:pt最后读入的数据不包含图片pixel_value pending This problem is yet to be addressed
#4707 opened Jul 7, 2024 by RONINGOD updated Jul 8, 2024
1 task done
@BUAADreamer
Phi-3-small Different Chat Template pending This problem is yet to be addressed
#4712 opened Jul 7, 2024 by maksimstw updated Jul 8, 2024
1 task done
疑问：历史消息在训练时可以只作为上文不参与模型的预测吗？~ pending This problem is yet to be addressed
#4684 opened Jul 4, 2024 by ylsdamxssjxxdd updated Jul 7, 2024
1 task done
1
同配置和环境下从检查点继续训练OOM pending This problem is yet to be addressed
#4710 opened Jul 7, 2024 by Mr-KenLee updated Jul 7, 2024
1 task done
间歇性 RuntimeError: CUDA error: an illegal memory access was encounteredCUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect pending This problem is yet to be addressed
#4709 opened Jul 7, 2024 by Gierry updated Jul 7, 2024
1 task done
使用readme中提供的hugging face预训练数据集报错 pending This problem is yet to be addressed
#4708 opened Jul 7, 2024 by xiao-liya updated Jul 7, 2024
1 task done
triton.runtime.autotuner.OutOfResources pending This problem is yet to be addressed
#4688 opened Jul 5, 2024 by GitIgnoreMaybe updated Jul 7, 2024
1 task done
5
Plan for Documentation? pending This problem is yet to be addressed
#4703 opened Jul 6, 2024 by sangttruong updated Jul 6, 2024
3
Yi的template存在问题（附简单测试代码） pending This problem is yet to be addressed
#4699 opened Jul 6, 2024 by rangehow updated Jul 6, 2024
1 task done
Invalid device string: 'float32' pending This problem is yet to be addressed
#4698 opened Jul 6, 2024 by OnewayLab updated Jul 6, 2024
1 task done
1
WARNING:root:Some parameters are on the meta device device because they were offloaded to the cpu. pending This problem is yet to be addressed
#4697 opened Jul 5, 2024 by stromyu520 updated Jul 5, 2024
1 task done
Feature request: is Adam-mini optimizer worth adding? pending This problem is yet to be addressed
#4696 opened Jul 5, 2024 by jim-plus updated Jul 5, 2024
1 task done
大模型运行推理的时候，请求日志，打印重复 pending This problem is yet to be addressed
#4690 opened Jul 5, 2024 by caijx168 updated Jul 5, 2024
1 task done
qwen2 72b 910b lora后merge生成的权重 推理失败 npu This problem is related to NPU devices pending This problem is yet to be addressed
#4659 opened Jul 3, 2024 by wphtrying updated Jul 3, 2024
1 task done
ValueError: Failed to convert pandas DataFrame to Arrow Table from file pending This problem is yet to be addressed
#4650 opened Jul 2, 2024 by fzp0424 updated Jul 2, 2024
1 task done
[PPU]大佬有对ppu环境进行过测试么 pending This problem is yet to be addressed
#4606 opened Jun 28, 2024 by willionZS updated Jul 2, 2024
1 task done
1
Unable to run model.generate() for MoD model pending This problem is yet to be addressed
#4063 opened Jun 4, 2024 by Zkli-hub updated Jul 2, 2024
1 task done
3
ProTip! Mix and match filters to narrow down what you’re looking for.