Skip to content

Issues: allenai/RL4LMs

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

46 Open 13 Closed
46 Open 13 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

An Issues about RuntimeError
#76 opened Nov 8, 2024 by hanninaa
assert self.name.count("/") == 1
#75 opened Sep 21, 2024 by gangancuicuia
Which version of pip should we use when we try to set up the environment?
#73 opened Sep 8, 2024 by Wwwendyy
2
An issue happened when I set up
#72 opened Sep 7, 2024 by Wwwendyy
Question about the classifier used for IntentAccuracyDailyDialog.
#71 opened Apr 24, 2024 by zhangjf-nlp
Upgrade to torch 2.0
#69 opened Feb 9, 2024 by agastyaseth
1
how to stop env parallel multi-process to debug env.step()?
#68 opened Dec 28, 2023 by invoker-LL
Is PPO really better than SFT (in general)? under the condition of same amount of data
#66 opened Nov 26, 2023 by allanj
1
Do you have any plans to apply the recently published Reinforced Self-Training (ReST)?
#65 opened Sep 8, 2023 by missflash
Pip install error with gym and torch
#64 opened Jul 14, 2023 by BaleChen
3
NLPO Code Error and Query About gymnasium vs gym Usage
#63 opened Jul 7, 2023 by jinyilun718
Reproducing existing results on NarrativeQA
#62 opened Jul 7, 2023 by yxk23
Memory issue in metric evals?
#61 opened Jun 23, 2023 by AnujMahajanOxf
is multi-dimensional reward supported?
#60 opened Jun 13, 2023 by zabir-nabil
CPU Support Minor Bug
#59 opened Jun 9, 2023 by tedmoskovitz
model.generate.scores returning two scores
#57 opened May 14, 2023 by debjitpaul
'GPT2Model' object has no attribute 'first_device'
#56 opened May 8, 2023 by Stephanehk
Using GPT-2
#55 opened Apr 29, 2023 by oroojlooy
How can I inference data with the model after PPO training?
#54 opened Apr 28, 2023 by RyanYip-Kat
Bug while loading t5 base model
#53 opened Apr 25, 2023 by Sahajtomar
1
Error with Accelerate integration + NLPO
#52 opened Apr 13, 2023 by avacaondata
1
[Question] End-to-end example
#51 opened Apr 4, 2023 by farrokhsiar
In the paper, what is the detail setting of supervised learning? Is SL has additional supervised data?
#49 opened Mar 29, 2023 by guotong1988
A question bother me a long time: What is the difference between RL-for-text-generation and delete-0-reward-model-predictions?
#46 opened Mar 16, 2023 by guotong1988
Bloom Supporting
#44 opened Mar 13, 2023 by c-box
3
ProTip! no:milestone will show everything without a milestone.