Skip to content

Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free

active 2024-02-072025-06-23 (UTC)

Partial coverage17,566 / 22,569 hourly files (78%) · 2 absent upstream · 5,002 failed, retryable2024-01-152026-08-12 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
181
Pushes
12
Pull requests
5
Issues
15
Stars
104
Forks
13

Activity over time

Daily event counts in the loaded window

Line chart, 503 days from 2024-02-07 to 2025-06-23. Pushes: 12 total, peak 3 in a day. Pull requests: 5 total, peak 2 in a day. Issues: 15 total, peak 4 in a day. Comments: 29 total, peak 6 in a day. Stars: 104 total, peak 28 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

ContributorContributionsPushesPRsComments
Locutusque3912319
IsNoobgrammer11026
fakerybakery5002
windmaple4002
michaelifebrian1000
staticpunch1000

Recent activity

Latest issues, pull requests and releases

  • Issue comment#14Locutusque2024-10-31 20:33
    GPT2 Rules
  • Issue#14Locutusque2024-10-31 20:33
    GPT2 Rules
  • Issue#14michaelifebrian2024-10-31 07:43
    GPT2 Rules
  • Issue comment#13Locutusque2024-06-03 23:44
    Full finetune or LoRA?
  • Issue#13Locutusque2024-06-03 23:44
    Full finetune or LoRA?
  • Issue#13staticpunch2024-06-03 04:30
    Full finetune or LoRA?
  • Issue comment#11Locutusque2024-05-15 23:15
    Support for LLama like models (Deepseek)
  • Issue#11Locutusque2024-05-15 23:15
    Support for LLama like models (Deepseek)
  • Issue comment#11Locutusque2024-04-23 22:46
    Support for LLama like models (Deepseek)
  • Pull request#10Locutusque2024-03-09 19:21
  • Issue comment#10Locutusque2024-03-09 19:21
    SM3 Optimizer + other memory optimizations
  • Issue comment#10IsNoobgrammer2024-03-09 19:18
    SM3 Optimizer + other memory optimizations
  • Issue comment#10Locutusque2024-03-09 18:56
    SM3 Optimizer + other memory optimizations
  • Pull request#10IsNoobgrammer2024-03-09 18:46
  • Issue comment#9Locutusque2024-03-08 01:58
    dataset
  • Issue#7Locutusque2024-03-01 21:00
    [feature request] Add support for Google Gemma models
  • Pull request#8Locutusque2024-03-01 21:00
  • Issue comment#8Locutusque2024-03-01 21:00
    Add support Gemma , Smoothed Loss Fn, fix typo , val_steps, Better Wandb Logging
  • Issue comment#7IsNoobgrammer2024-02-29 10:54
    [feature request] Add support for Google Gemma models
  • Pull request#8IsNoobgrammer2024-02-29 10:34
  • Issue#6IsNoobgrammer2024-02-29 10:22
    Incorrect implementation for calculating loss
  • Issue comment#7Locutusque2024-02-25 21:31
    [feature request] Add support for Google Gemma models
  • Issue comment#7Locutusque2024-02-22 01:27
    [feature request] Add support for Google Gemma models
  • Issue comment#6Locutusque2024-02-18 23:25
    Incorrect implementation for calculating loss
  • Issue#6IsNoobgrammer2024-02-18 20:45
    Incorrect implementation for calculating loss

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 104 stars here means stars gained during the window, not the repo's star count.