The open-source repository for PAL: Sample-Efficient Personalized Reward Modeling for Pluralistic Alignment.
active 2025-02-08 → 2025-12-30 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 326 days from 2025-02-08 to 2025-12-30. Pushes: 3 total, peak 1 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 8 total, peak 2 in a day. Comments: 7 total, peak 2 in a day. Stars: 10 total, peak 2 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| ChenDaiwei-99 | 11 | 2 | 0 | 5 |
| Lsayan | 6 | 0 | 0 | 2 |
| zachhendon | 2 | 0 | 2 | 0 |
| aniketrege | 1 | 1 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#8ChenDaiwei-992025-08-28 04:46The implementation of fixed LLM
- Issue comment#8ChenDaiwei-992025-08-28 02:59The implementation of fixed LLM
- Issue#7Lsayan2025-06-14 13:03Specifing User ID while inference
- Issue#6Lsayan2025-06-10 19:31Inference Code for getting the reward score
- Issue#3ChenDaiwei-992025-05-11 01:55ValueError: Can't find 'adapter_config.json' at 'daiweichen/pal-b-large-opt-350m'
- Issue#5ChenDaiwei-992025-05-11 01:55Inferencing code on the reward model
- Issue comment#5ChenDaiwei-992025-04-26 16:40Inferencing code on the reward model
- Issue comment#5Lsayan2025-04-26 16:08Inferencing code on the reward model
- Issue#5Lsayan2025-04-25 17:22What is the format of input for inferencing.
- Issue#2ChenDaiwei-992025-04-22 05:18Can the trained reward model be created without adapter layers?
- Issue comment#2ChenDaiwei-992025-04-22 05:18Can the trained reward model be created without adapter layers?
- Pull request#4zachhendon2025-04-21 19:08
- Issue comment#2Lsayan2025-04-19 19:00Can the trained reward model be created without adapter layers?
- Issue comment#3ChenDaiwei-992025-04-17 23:40ValueError: Can't find 'adapter_config.json' at 'daiweichen/pal-b-large-opt-350m'
- Issue comment#2ChenDaiwei-992025-04-17 22:57Can the trained reward model be created without adapter layers?
- Pull request#4zachhendon2025-04-17 03:13
- Issue#3Lsayan2025-04-14 20:51ValueError: Can't find 'adapter_config.json' at 'daiweichen/pal-b-large-opt-350m'
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 10 stars here means stars gained during the window, not the repo's star count.