Activity over time
Daily event counts in the loaded window
Line chart, 652 days from 2024-06-24 to 2026-04-06. Pushes: 50 total, peak 30 in a day. Pull requests: 6 total, peak 2 in a day. Issues: 28 total, peak 4 in a day. Comments: 40 total, peak 8 in a day. Stars: 582 total, peak 46 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 |
|---|---|---|---|---|
| angelahzyuan | 46 | 29 | 3 | 14 |
| MeckyWu | 25 | 21 | 0 | 3 |
| kaykyr | 14 | 0 | 0 | 7 |
| hodachi-axcxept | 9 | 0 | 0 | 7 |
| aman2304 | 3 | 0 | 1 | 1 |
| srzhu97 | 3 | 0 | 0 | 1 |
| deep-throat-in-me | 2 | 0 | 0 | 1 |
| LikhonX | 2 | 0 | 0 | 0 |
| xiaohangt | 2 | 0 | 1 | 1 |
| qy1026 | 2 | 0 | 0 | 0 |
| xinghuang2050 | 2 | 0 | 0 | 0 |
| xukp20 | 2 | 0 | 0 | 1 |
| Jackory | 2 | 0 | 0 | 1 |
| swyoon | 2 | 0 | 0 | 2 |
| sanowl | 1 | 0 | 1 | 0 |
| RandomInternetPreson | 1 | 0 | 0 | 0 |
| blackblue9 | 1 | 0 | 0 | 0 |
| skramer-dev | 1 | 0 | 0 | 0 |
| Kquant03 | 1 | 0 | 0 | 0 |
| namdw | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#27MeckyWu2024-10-09 18:20Discrepancy in rm_scores Length for Mistral-7B-SPPO Iter1 Dataset
- Issue#27srzhu972024-10-09 06:56Discrepancy in rm_scores Length for Mistral-7B-SPPO Iter1 Dataset
- Issue comment#26srzhu972024-10-09 06:40Release training dataset and loss log to help reproduce results
- Issue#26srzhu972024-10-09 06:38Release training dataset and loss log to help reproduce results
- Issue comment#15MeckyWu2024-09-18 20:04Scores and probability calcuations
- Issue comment#24aman23042024-09-09 17:03Modify generate.sh to take a dynamic number of GPUs as input
- Issue#25aman23042024-09-02 00:27Added a new PR to allow generation on fewer than 8 GPUs
- Pull request#24aman23042024-09-02 00:25
- Issue comment#23MeckyWu2024-08-24 21:37Typo here
- Issue#23MeckyWu2024-08-24 21:37Typo here
- Issue#23xukp202024-08-24 06:44Typo here
- Issue comment#15xukp202024-08-24 06:23Scores and probability calcuations
- Issue comment#12Arnav04002024-08-07 08:47Dataset used and results in Gemma-2-9B results
- Issue#22yesiam-png2024-07-23 07:46DPO baseline implementation
- Issue comment#8angelahzyuan2024-07-14 03:34Is it normal the pipeline start with a huge loss ?
- Pull request#19angelahzyuan2024-07-13 23:35
- Pull request#11angelahzyuan2024-07-13 23:19
- Issue#21kaykyr2024-07-11 16:03SPPO Implementation on Axolotl!
- Issue comment#19xiaohangt2024-07-11 06:38Flexible GPU specification in generate.sh
- Issue comment#19deep-throat-in-me2024-07-11 01:31Flexible GPU specification in generate.sh
- Issue#20deep-throat-in-me2024-07-11 01:11[Question] Sampling Parameters for Response Generation
- Issue#16kaykyr2024-07-10 23:55Adaptation for 4-bit Quantization Training/Responses Generation (with 2 Home GPUs)
- Pull request#19xiaohangt2024-07-10 23:07
- Issue comment#8kaykyr2024-07-10 19:26Is it normal the pipeline start with a huge loss ?
- Issue comment#16kaykyr2024-07-10 19:25Adaptation for 4-bit Quantization Training/Responses Generation (with 2 Home GPUs)
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 582 stars here means stars gained during the window, not the repo's star count.