Skip to content

The SFT phase of LIFT based on PiSSA.

active 2024-04-112026-01-24 (UTC)

Partial coverage16,293 / 20,473 hourly files (80%) · 2 absent upstream · 4,179 failed, retryable2024-04-112026-08-12 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
347
Pushes
54
Pull requests
2
Issues
40
Stars
192
Forks
13

Activity over time

Daily event counts in the loaded window

Line chart, 654 days from 2024-04-11 to 2026-01-24. Pushes: 54 total, peak 9 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 40 total, peak 8 in a day. Comments: 46 total, peak 5 in a day. Stars: 192 total, peak 7 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#48UnbearableFate2025-11-21 06:04
    How to adjust hyperparameters when PiSSA initialization underperforms while vanilla LoRA + Kaiming works well?
  • Issue#46thistleknot2025-09-18 01:54
    Dual Adapters
  • Issue comment#45gapsong2025-09-03 10:28
    Difference LoftQ and qPissa
  • Issue comment#45fxmeng2025-09-03 09:55
    Difference LoftQ and qPissa
  • Issue#45gapsong2025-09-03 09:34
    Difference LoftQ and qPissa
  • Issue comment#45gapsong2025-09-01 14:22
    Difference LoftQ and qPissa
  • Issue comment#45gapsong2025-09-01 14:21
    Difference LoftQ and qPissa
  • Issue#45gapsong2025-09-01 14:21
    Difference LoftQ and qPissa
  • Issue comment#38Peng-YM2025-09-01 02:11
    High Initial Loss When Fine-Tuning Gemma Model
  • Issue comment#45fxmeng2025-08-31 02:46
    Difference LoftQ and qPissa
  • Issue comment#38gapsong2025-07-29 12:26
    High Initial Loss When Fine-Tuning Gemma Model
  • Issue#44SpeeeedLee2025-07-10 07:37
    Code for Mistral and Qwen
  • Issue#43TracyGuo20012025-06-29 14:41
    error on evaluating Floating point exceptionpython
  • Issue comment#40yuxuan-z192025-06-02 14:16
    KeyError: 'tokenizer'
  • Issue#36LonglongaaaGo2025-05-10 15:08
    How to apply on the FacebookAI/roberta-large model?
  • Issue comment#38Peng-YM2025-02-11 03:37
    High Initial Loss When Fine-Tuning Gemma Model
  • Issue#38zhangzc212025-01-24 06:52
    High Initial Loss When Fine-Tuning Gemma Model
  • Issue comment#32LonglongaaaGo2025-01-18 23:40
    Reproduce the results shown in Table 1
  • Issue comment#34chuangzhidan2025-01-10 02:05
    ImportError: cannot import name 'PiSSAConfig' from 'peft' (/usr/local/lib/python3.10/dist-packages/peft/init.py)
  • Issue comment#32LonglongaaaGo2025-01-05 19:21
    Reproduce the results shown in Table 1
  • Issue#35LZY-the-boys2025-01-04 05:44
    Question about Scaling
  • Issue#34chuangzhidan2025-01-02 08:12
    ImportError: cannot import name 'PiSSAConfig' from 'peft' (/usr/local/lib/python3.10/dist-packages/peft/init.py)
  • Issue comment#33chuangzhidan2025-01-02 08:03
    Issue with `ImportError: cannot import name 'CloverConfig'`
  • Issue#33cmu3922025-01-02 06:44
    Issue with `ImportError: cannot import name 'CloverConfig'`
  • Issue comment#33chuangzhidan2025-01-01 15:31
    Issue with `ImportError: cannot import name 'CloverConfig'`

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 192 stars here means stars gained during the window, not the repo's star count.