Minimal reproduction of OneRec
Python · active 2025-10-23 → 2026-08-06 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 288 days from 2025-10-23 to 2026-08-06. Pushes: 78 total, peak 20 in a day. Pull requests: 4 total, peak 1 in a day. Issues: 28 total, peak 6 in a day. Comments: 50 total, peak 5 in a day. Stars: 483 total, peak 26 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 |
|---|---|---|---|---|
| AkaliKong | 105 | 78 | 0 | 19 |
| gzj-ai | 7 | 0 | 0 | 2 |
| cocoshe | 5 | 0 | 1 | 3 |
| ashleys0 | 2 | 0 | 0 | 1 |
| WindSighiii | 2 | 0 | 0 | 2 |
| iFe1er | 2 | 0 | 0 | 1 |
| fukairui | 2 | 0 | 0 | 2 |
| fukioston | 2 | 0 | 0 | 2 |
| lyzltysgithub | 2 | 0 | 0 | 1 |
| LNH2002 | 2 | 0 | 0 | 2 |
| newwindhxx | 2 | 0 | 0 | 2 |
| lms-design | 1 | 0 | 0 | 0 |
| lovemaoli | 1 | 0 | 1 | 0 |
| yijingshihenxiule | 1 | 0 | 0 | 0 |
| cookieminions | 1 | 0 | 0 | 1 |
| jbdcia321vw | 1 | 0 | 0 | 1 |
| hupeiyu21 | 1 | 0 | 0 | 1 |
| jiangzizi | 1 | 0 | 0 | 1 |
| Richard-zrx | 1 | 0 | 1 | 0 |
| xiaoxian-x | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#66WindSighiii2026-03-08 07:31在RL训练的时候开启test_during_training=True会导致大量no valid token的wanring
- Issue comment#66WindSighiii2026-03-08 07:26在RL训练的时候开启test_during_training=True会导致大量no valid token的wanring
- Issue#64yijingshihenxiule2026-03-03 13:05模型部署问题
- Issue comment#58LNH20022026-03-03 04:48强化学习（RL）后模型性能下降
- Issue#59xym06012026-02-28 06:37sinkhorn的计算问题
- Issue comment#58LNH20022026-02-22 04:03强化学习（RL）后模型性能下降
- Issue#61xiaoxian-x2026-02-13 07:43设置freeze_LLM=True 时 运行sft.py 报 NameError: original_vocab_size 未定义
- Issue#60sullicsullic2026-02-12 08:03rqvae训练问题
- Pull request#57cocoshe2026-02-01 07:37
- Issue comment#55cocoshe2026-01-31 14:21Fluctuations in Reinforcement Learning Rewards
- Issue comment#56Gavin-Cool2026-01-30 03:56测试的时候非常多UserWarning: No valid tokens found for hash_key
- Issue comment#55fukioston2026-01-30 02:14Fluctuations in Reinforcement Learning Rewards
- Issue comment#49SuperTom992026-01-29 17:04关于文章结果复现的问题
- Issue comment#51fukioston2026-01-21 14:07您好，为什么不用训练好的 codebook hidden 做LLM新增token维度的初始化呢
- Issue comment#54lyzltysgithub2026-01-21 06:27贴一个用BPE分词的BUG
- Issue comment#49lenbow2026-01-12 03:56关于文章结果复现的问题
- Issue comment#49Luo-Jiaming2026-01-08 09:56关于文章结果复现的问题
- Issue#50lyzltysgithub2026-01-04 15:11`ConstrainedLogitsProcessor` constraint fails when `prefix_allowed_tokens_fn` returns empty list, causing unconstrained random sampling
- Issue#47rijinjjjj2025-12-29 13:51关于复现文章中baseline的问题
- Issue comment#45ashleys02025-12-20 05:33Is Qwen2.5-1.5B-Instruction Required to Reproduce Results?
- Issue comment#44newwindhxx2025-12-17 17:08Reproducing -- test performance degrades after RL step
- Issue comment#35newwindhxx2025-12-17 17:03Reproduction Results of SFT and RL Are Lower Than Reported — Any Suggestions?
- Pull request#46lovemaoli2025-12-17 11:28
- Issue#38lms-design2025-12-10 08:25Item Embedding
- Issue#44ashleys02025-12-09 07:27Reproducing -- test performance degrades after RL step
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 483 stars here means stars gained during the window, not the repo's star count.