Skip to content

Try SPIN and combine with IL.

active 2024-02-092026-03-26 (UTC)

Complete coverage26,687 / 26,687 hourly files (100%) · 2 absent upstream2023-08-152026-08-30 (UTC)
Events
1.4K
Pushes
38
Pull requests
12
Issues
41
Stars
1.2K
Forks
100

Activity over time

Daily event counts in the loaded window

Line chart, 777 days from 2024-02-09 to 2026-03-26. Pushes: 38 total, peak 13 in a day. Pull requests: 12 total, peak 3 in a day. Issues: 41 total, peak 4 in a day. Comments: 75 total, peak 9 in a day. Stars: 1,151 total, peak 112 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

Recent activity

Latest issues, pull requests and releases

  • Issue#43BarCodeReader2025-07-21 15:55
    some questions about the process
  • Issue#41NZ-Liam-Zhong2025-02-12 10:20
    Nothing wrong.
  • Issue comment#41NZ-Liam-Zhong2025-02-12 10:19
    Nothing wrong.
  • Issue comment#41NZ-Liam-Zhong2025-02-12 10:07
    The code is wrong.
  • Issue comment#39GGgrey2024-12-26 08:31
    Can't reproduce the result
  • Issue#39GGgrey2024-12-26 07:12
    Can't reproduce the result
  • Issue comment#37junming-yang2024-11-04 02:40
    Hello, I would like to ask, when you are training the model, do you only use the first round of dialogue from the ultrachat_200k?
  • Issue#38kang-09092024-10-25 05:29
    Question about potential overfitting
  • Issue comment#20TanZhendong2024-10-22 12:35
    What changes should I make to apply the SPIN method on Llama2?
  • Issue comment#34jojo233332024-08-23 18:25
    OOM with 8 A800
  • Issue comment#34angelahzyuan2024-08-22 05:16
    OOM with 8 A800
  • Issue comment#34jojo233332024-08-15 04:22
    OOM with 8 A800
  • Issue comment#34angelahzyuan2024-08-14 17:17
    OOM with 8 A800
  • Issue comment#34jojo233332024-08-13 01:31
    OOM with 8 A800
  • Issue#37jackwwy2024-07-21 12:51
    Hello, I would like to ask, when you are training the model, do you only use the first round of dialogue from the ultrachat_200k?
  • Issue comment#34647sherry2024-07-18 08:12
    OOM with 8 A800
  • Issue comment#35jiangjun01052024-07-18 00:56
    numpy version warnings
  • Issue comment#34angelahzyuan2024-07-13 23:28
    OOM with 8 A800
  • Issue comment#36Joyyang1582024-07-12 22:18
    Cannot reproduce the result
  • Issue comment#36angelahzyuan2024-07-12 22:05
    Cannot reproduce the result
  • Issue comment#36Joyyang1582024-07-12 22:03
    Cannot reproduce the result
  • Issue comment#36angelahzyuan2024-07-12 21:56
    Cannot reproduce the result
  • Issue#36Joyyang1582024-07-12 21:47
    Cannot reproduce the result
  • Issue#35jiangjun01052024-07-09 02:28
    numpy version warnings
  • Issue#34647sherry2024-07-08 08:32
    OOM with 8 A800

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,151 stars here means stars gained during the window, not the repo's star count.