This repo contains the source code for the paper "Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning"
Python · active 2025-09-29 → 2026-06-18 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 263 days from 2025-09-29 to 2026-06-18. Pushes: 23 total, peak 5 in a day. Pull requests: 18 total, peak 5 in a day. Issues: 3 total, peak 1 in a day. Comments: 17 total, peak 3 in a day. Stars: 126 total, peak 41 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 |
|---|---|---|---|---|
| dibbla | 20 | 2 | 7 | 9 |
| VsonicV | 19 | 14 | 0 | 3 |
| conorfhayes | 7 | 4 | 0 | 1 |
| DayDreamChaser | 5 | 0 | 4 | 1 |
| sunrainyg | 4 | 3 | 1 | 0 |
| mhrezaei1 | 4 | 0 | 4 | 0 |
| YuvrajSingh-mist | 2 | 0 | 0 | 1 |
| szs777 | 1 | 0 | 0 | 1 |
| AnMakc | 1 | 0 | 1 | 0 |
| rajsr-p | 1 | 0 | 0 | 1 |
| jharkfinn | 1 | 0 | 1 | 0 |
| yannikkellerde | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#43dibbla2026-02-12 08:16
- Pull request#43dibbla2026-02-12 08:16
- Issue#41dibbla2026-02-10 20:57[issue] AttributeError with QwenTokenizer for accelerated version
- Issue comment#41dibbla2026-02-10 20:57[issue] AttributeError with QwenTokenizer for accelerated version
- Issue comment#41YuvrajSingh-mist2026-02-10 12:19[issue] AttributeError with QwenTokenizer for accelerated version
- Issue comment#41dibbla2026-02-07 19:37[issue] AttributeError with QwenTokenizer for accelerated version
- Issue comment#41dibbla2026-02-07 17:51[issue] AttributeError with QwenTokenizer for accelerated version
- Issue comment#41rajsr-p2026-02-07 02:38[issue] AttributeError with QwenTokenizer for accelerated version
- Issue comment#41dibbla2026-02-06 19:24[issue] AttributeError with QwenTokenizer for accelerated version
- Issue comment#40dibbla2026-02-06 19:20Questions about applying the proposed algorithm to diffusion models
- Issue#41YuvrajSingh-mist2026-02-05 19:05[issue] AttributeError with QwenTokenizer for accelerated version
- Issue comment#25VsonicV2025-11-12 03:30Request to evaluate code
- Issue comment#25szs7772025-11-12 01:12Request to evaluate code
- Pull request#29dibbla2025-11-07 07:02
- Pull request#28dibbla2025-11-07 06:36
- Pull request#28dibbla2025-11-07 06:35
- Issue comment#25VsonicV2025-11-05 07:41Request to evaluate code
- Pull request#26sunrainyg2025-11-05 06:35
- Pull request#20jharkfinn2025-10-27 00:32
- Pull request#17dibbla2025-10-20 05:43
- Pull request#17dibbla2025-10-20 05:43
- Issue#4yannikkellerde2025-10-08 12:47Question about expected runtime of the algorithm
- Pull request#3AnMakc2025-10-08 12:14
- Pull request#2DayDreamChaser2025-10-08 11:57
- Pull request#2DayDreamChaser2025-10-08 11:54
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 126 stars here means stars gained during the window, not the repo's star count.