[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
45 Open 4,067 Closed
45 Open 4,067 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

推理阶段，预测文件中label显示不全问题 bug Something isn't working pending This problem is yet to be addressed
#3775 opened May 16, 2024 by jy-101361-1810897
1 task done
1
PPO使用zero3加载全参训练的奖励模型，奖励模型加载失败。 bug Something isn't working pending This problem is yet to be addressed
#1790 opened Dec 11, 2023 by Luoxiaohei41
12
Have we added VeRA (Vector Based Random Matrix Adaption) , it recently got published at ICLR 2024 pending This problem is yet to be addressed
#2238 opened Jan 18, 2024 by Akshay1-6180
sft_packing实现的问题 pending This problem is yet to be addressed
#2289 opened Jan 22, 2024 by dyh1996
1 task done
2
7
[Feature request / help] Evaluate on different dataset to training dataset pending This problem is yet to be addressed
#2290 opened Jan 22, 2024 by Peter-Devine
1 task done
1
奖励模型断点续训报错 good first issue Good for newcomers pending This problem is yet to be addressed
#2351 opened Jan 26, 2024 by zhanglv0209
6
[TODO] Update merging QLoRA workaround pending This problem is yet to be addressed
#2448 opened Feb 6, 2024 by hiyouga
Erroneous/high loss with DeepSpeed Zero3 and bf16 pending This problem is yet to be addressed
#2483 opened Feb 15, 2024 by mnmueller
1 task done
有计划支持LoRAMoE吗？ pending This problem is yet to be addressed
#2749 opened Mar 8, 2024 by luyuntao92
1 task done
8
Feature Request: Support Representation Fine-Tuning (ReFT) pending This problem is yet to be addressed
#3183 opened Apr 8, 2024 by indiejoseph
1 task done
report to wandb能自动记录本项目里新增的参数么？例如stage、dataset、lora_rank、cutoff_len这些，暂时没看到有上报 enhancement New feature or request pending This problem is yet to be addressed
#3462 opened Apr 26, 2024 by onebula
1 task done
3
FSDP QDoRa pending This problem is yet to be addressed
#3550 opened May 2, 2024 by etemiz
1 task done
9
Ideas behind sharing parameters of policy model and value model? enhancement New feature or request pending This problem is yet to be addressed
#1563 opened Nov 19, 2023 by MagiaSN
9
Output difference between LLaMA-Factory and llama.cpp pending This problem is yet to be addressed
#3563 opened May 3, 2024 by anidh
1 task done
2
errors while in finetune intermlm2-chat-20b with qlora pending This problem is yet to be addressed
#3798 opened May 17, 2024 by a1exyu
1 task done
1
昇腾多卡训练问题 npu This problem is related to NPU devices pending This problem is yet to be addressed
#3810 opened May 19, 2024 by 1737686924
1 task done
Phi-3-small exploding gradient issue. pending This problem is yet to be addressed
#3881 opened May 23, 2024 by HideLord
1 task done
3
对于微调分类任务，如何在使用api inference时获取输出标签置信分数 enhancement New feature or request pending This problem is yet to be addressed
#3932 opened May 28, 2024 by xhdu
1 task done
6
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning enhancement New feature or request pending This problem is yet to be addressed
#3970 opened May 29, 2024 by backroom-coder
MODPO: Multi-Objective Direct Preference Optimization enhancement New feature or request pending This problem is yet to be addressed
#3973 opened May 30, 2024 by AlexYoung757
How to specify eval set during training process? pending This problem is yet to be addressed
#3974 opened May 30, 2024 by may012345
1 task done
Feature suggestion: cutoff_len could optionally drop too long examples from dataset. pending This problem is yet to be addressed
#3995 opened May 30, 2024 by s4s0l
1
用openai库 请求时，流式请求时缺stream_options={"include_usage": True}的处理，用于计算流式tokens pending This problem is yet to be addressed
#3998 opened May 30, 2024 by sasicDHH
1 task done
Unable to run model.generate() for MoD model pending This problem is yet to be addressed
#4063 opened Jun 4, 2024 by Zkli-hub
1 task done
2
Yi-1.5-9B推理gpu利用率为0 pending This problem is yet to be addressed
#4628 opened Jul 1, 2024 by Jack-mi
1 task done
1
ProTip! Follow long discussions with comments:>50.