Source code of "Reasons to Reject? Aligning Language Models with Judgments"
active 2023-12-22 → 2025-01-09 (UTC)
Complete coverage26,631 / 26,631 hourly files (100%) · 2 absent upstream2023-08-15 → 2026-08-28 (UTC)
Events
114
Pushes
33
Pull requests
0
Issues
7
Stars
58
Forks
4
Activity over time
Daily event counts in the loaded window
Line chart, 385 days from 2023-12-22 to 2025-01-09. Pushes: 33 total, peak 10 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 7 total, peak 1 in a day. Comments: 8 total, peak 2 in a day. Stars: 58 total, peak 14 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
Recent activity
Latest issues, pull requests and releases
- Issue comment#4lx861102024-04-28 08:57训练异常
- Issue comment#4wwxu212024-04-17 08:40训练异常
- Issue comment#4lx861102024-04-12 10:04训练异常
- Issue#4lx861102024-04-12 10:04训练异常
- Issue#3yqt2024-03-29 07:00What is the checkpoint initialized from in DPO training settings?
- Issue comment#3wwxu212024-03-25 02:31What is the checkpoint initialized from in DPO training settings?
- Issue#3yqt2024-03-21 03:20What is the checkpoint initialized from in DPO training settings?
- Issue#2wwxu212024-03-09 14:24Why loss become zero?
- Issue comment#2wwxu212024-03-06 12:27Why loss become zero?
- Issue#2Labmem0092024-03-06 03:39Why loss become zero?
- Issue#1wwxu212024-01-18 06:25Is there a script for offline alignment and full fine-tune? And what about catastrophic forgetting？
- Issue comment#1Labmem0092024-01-12 03:25Is there a script for offline alignment and full fine-tune? And what about catastrophic forgetting？
- Issue comment#1Labmem0092024-01-12 03:07Is there a script for offline alignment and full fine-tune? And what about catastrophic forgetting？
- Issue comment#1wwxu212024-01-11 05:09Is there a script for offline alignment and full fine-tune? And what about catastrophic forgetting？
- Issue#1Labmem0092024-01-11 03:58Is there a script for offline alignment and full fine-tune? And what about catastrophic forgetting？
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 58 stars here means stars gained during the window, not the repo's star count.