An Easy-to-use, Scalable and High-performance RLHF Framework (Support 70B+ full tuning & LoRA & Mixtral & KTO)
Python · active 2023-11-06 → 2024-07-17 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 255 days from 2023-11-06 to 2024-07-17. Pushes: 483 total, peak 33 in a day. Pull requests: 103 total, peak 4 in a day. Issues: 167 total, peak 6 in a day. Comments: 440 total, peak 36 in a day. Stars: 953 total, peak 40 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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| hijkzzz | 780 | 468 | 61 | 191 |
| wuxibin89 | 81 | 10 | 9 | 50 |
| catqaq | 34 | 5 | 5 | 13 |
| karthik-nexusflow | 22 | 0 | 0 | 19 |
| paulcx | 20 | 0 | 0 | 15 |
| karthik19967829 | 17 | 0 | 0 | 14 |
| mickelliu | 16 | 0 | 4 | 10 |
| ZiyiLiubird | 12 | 0 | 0 | 5 |
| mgerstgrasser | 12 | 0 | 1 | 7 |
| victorShawFan | 11 | 0 | 0 | 6 |
| louieworth | 9 | 0 | 0 | 7 |
| hehebamei | 9 | 0 | 0 | 6 |
| zhanghaoie | 8 | 0 | 0 | 6 |
| eyuansu62 | 8 | 0 | 0 | 5 |
| LSC527 | 8 | 0 | 0 | 4 |
| NZ99 | 7 | 0 | 0 | 7 |
| mickel-liu | 7 | 0 | 0 | 4 |
| yangzhipeng1108 | 7 | 0 | 0 | 2 |
| tianhao-nexusflow | 7 | 0 | 0 | 6 |
| ZhaofengWu | 7 | 0 | 0 | 4 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#361hijkzzz2024-07-16 02:47support remote rm api for ppo and ppo ray
- Issue comment#361catqaq2024-07-16 02:36support remote rm api for ppo and ppo ray
- Releasehijkzzz2024-07-16 01:46Release v0.3.6
- Issue comment#361hijkzzz2024-07-15 23:47support remote rm api for ppo and ppo ray
- Issue#359hijkzzz2024-07-15 00:10Possible minor bug
- Issue#359ZhaofengWu2024-07-14 22:34Possible minor bug
- Issue#263hijkzzz2024-07-14 09:14[Baseline] LLaMA2-7B RLHF training curves
- Releasehijkzzz2024-07-13 23:26Release v0.3.5
- Issue comment#358hijkzzz2024-07-13 23:15vllm engine not working
- Issue comment#358babu1112024-07-13 13:50vllm engine not working
- Issue#358babu1112024-07-13 13:49vllm engine not working
- Issue#357babu1112024-07-13 13:47process groups for actor and vllm engine
- Issue comment#357hijkzzz2024-07-12 11:58process groups for actor and vllm engine
- Issue#357babu1112024-07-12 10:07process groups for actor and vllm engine
- Issue comment#354hijkzzz2024-07-12 07:49请问下rm 模型训练大概需要什么级别的显卡，需要几张？
- Issue comment#354hehebamei2024-07-12 06:41请问下rm 模型训练大概需要什么级别的显卡，需要几张？
- Issue comment#354hehebamei2024-07-12 06:41请问下rm 模型训练大概需要什么级别的显卡，需要几张？
- Issue comment#354hijkzzz2024-07-12 05:32请问下rm 模型训练大概需要什么级别的显卡，需要几张？
- Issue comment#354hehebamei2024-07-12 04:24请问下rm 模型训练大概需要什么级别的显卡，需要几张？
- Issue comment#354hijkzzz2024-07-12 03:38请问下rm 模型训练大概需要什么级别的显卡，需要几张？
- Issue comment#355hijkzzz2024-07-12 03:37load transformers' issue
- Issue#355chauncygu2024-07-12 03:36load transformers' issue
- Issue#354hehebamei2024-07-12 02:52请问下rm 模型训练大概需要什么级别的显卡，需要几张？
- Issue comment#353hijkzzz2024-07-11 23:13会不会支持异步生成训练
- Issue#351hijkzzz2024-07-10 23:59Qwen2-1.5b模型做sft微调报错padding_side='right'
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 953 stars here means stars gained during the window, not the repo's star count.