Skip to content

Issues: CarperAI/trlx

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

79 Open 211 Closed
79 Open 211 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

OOM error with PEFT LoRA on Llama2-7B bug Something isn't working
#601 opened Sep 20, 2024 by arpaiva
1
Load the checkpoint fails bug Something isn't working
#600 opened Sep 6, 2024 by AfraAmini
cannot import name 'flatten_dataclass' from 'trlx.data.ilql_types' bug Something isn't working
#599 opened Jul 31, 2024 by AfraAmini
maybe bug in prepare & load's order bug Something isn't working
#598 opened Jul 27, 2024 by daiwk
1
Error when running Ray Tune to launch hyperparameter sweep bug Something isn't working
#597 opened Jul 26, 2024 by Jing-L97
1
Crash when using save_state with deepspeed: model.state_dict functions incompatible with new deepspeed. bug Something isn't working
#596 opened Jul 11, 2024 by JohannesAck
Data Loader Bug when running t5_summarization_daily_cnn.py bug Something isn't working
#595 opened Jun 4, 2024 by yunanyan
Why train dataloader is not prepared by Accelerator bug Something isn't working
#594 opened May 18, 2024 by Jiaxin-Wen
TRLX Environment customization
#593 opened Apr 21, 2024 by heraldiclily
Issue of tensors share memory bug Something isn't working
#591 opened Apr 1, 2024 by heraldiclily
2
[New Feature Request] Add KTO feature request New feature or request
#590 opened Jan 27, 2024 by 1485840691-eng
RLHF text summarization diverges bug Something isn't working
#589 opened Jan 14, 2024 by AlisonWen
Integration of Self-Play Fine-Tuning (SPIN) Method for Enhancing Large Language Models feature request New feature or request
#588 opened Jan 11, 2024 by SeungyounShin
Runtime error when running examples (ilql_sentiments_t5.py) bug Something isn't working
#587 opened Jan 8, 2024 by youxiho1
2
MPT is not working bug Something isn't working
#585 opened Dec 12, 2023 by ouhenio
when i use trlx ppotrainer train a model llama 13b model, but saved huggingface mode ,but when it inference , it has some strange keys ,and the inference result did not show ,it also have no error , it seems the result disapper bug Something isn't working
#584 opened Dec 3, 2023 by ldh127
1
Attention mask when calculating log ratio for PPO
#582 opened Nov 23, 2023 by kmy17518
Multi-GPU training errors with peft bug Something isn't working
#581 opened Nov 20, 2023 by AliengirlLiv
1
Issue since most recent transformers update bug Something isn't working
#580 opened Nov 11, 2023 by siddharthverma314
1
multigpu support for summarization ppo example bug Something isn't working
#571 opened Oct 21, 2023 by sayan1101
3
Problem with LLama training with LoRA bug Something isn't working
#567 opened Oct 17, 2023 by freQuensy23-coder
3
Question about saving peft checkpoint bug Something isn't working
#565 opened Oct 13, 2023 by nhanph
2
How to generate reward-labeled dataset feature request New feature or request
#561 opened Sep 20, 2023 by mikkelmedm
How to train LLaMA2 on the summarize_rlhf example?
#559 opened Sep 12, 2023 by missflash
Increasing max new tokens for generation arguments lead to errors bug Something isn't working
#553 opened Sep 4, 2023 by wise-east
3
ProTip! no:milestone will show everything without a milestone.