Skip to content

Issues: August-murr/trl

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

7 Open 1 Closed
7 Open 1 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

Allow more flexibility in the new PPOTrainer (aka PPOTrainerv2) 🧒 good approach ❓ question Seeking clarification or more information
#11 opened Jan 16, 2025 by qgallouedec
dpo_vlm.py ❓ question Seeking clarification or more information
#10 opened Jan 12, 2025 by qgallouedec
5 of 9 tasks
5
DeepSpeed with trl
#9 opened Jan 6, 2025 by August-murr
7 of 9 tasks
2
Dataset type conversion utilities 🏋 DDPO Related to DDPO 🏋 DPO Related to DPO 🏋 GKD Related to GKD 🏋 Iterative SFT Related to Iterative SFT 🏋 KTO Related to KTO 🎯 optimal import sentence ❓ question Seeking clarification or more information
#8 opened Jan 6, 2025 by August-murr
9 tasks done
onlinedpo error when use deepspeed zero3 👖 action-adventure ✨ enhancement New feature or request 🏋 Iterative SFT Related to Iterative SFT 🎯 optimal import sentence ❓ question Seeking clarification or more information 🏋 RLOO Related to RLOO
#7 opened Jan 6, 2025 by August-murr
5 of 9 tasks
Dataset type conversion utilities 🐛 bug Something isn't working 📚 documentation Improvements or additions to documentation
#6 opened Jan 6, 2025 by qgallouedec
9 tasks done
1
Dummy question ❓ question Seeking clarification or more information
#5 opened Jan 4, 2025 by August-murr
ProTip! Adding no:label will show everything without a label.