Skip to content

google-deepmind/recurrentgemma

View on GitHub ↗Related repositories →

Open weights language model from Google DeepMind, based on Griffin.

active 2024-04-092026-05-10 (UTC)

Complete coverage26,610 / 26,610 hourly files (100%) · 2 absent upstream2023-08-152026-08-27 (UTC)
Events
723
Pushes
24
Pull requests
3
Issues
13
Stars
622
Forks
34

Activity over time

Daily event counts in the loaded window

Line chart, 762 days from 2024-04-09 to 2026-05-10. Pushes: 24 total, peak 6 in a day. Pull requests: 3 total, peak 1 in a day. Issues: 13 total, peak 2 in a day. Comments: 23 total, peak 3 in a day. Stars: 622 total, peak 140 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
Nush395231406
botev13507
SamSmithGDM4202
sohamde3300
tybalex3001
gmuraru3012
zhangmozhe3001
Fr0do2001
Meshwa4282001
Sunwood-ai-labs2010
tridao1001
h-zhao19971000
eltociear1010
google-cla[bot]1001
Mooler04101000

Recent activity

Latest issues, pull requests and releases

  • ReleaseNush3952026-02-06 11:01
    v1.0.1
  • ReleaseNush3952025-06-04 16:38
    Recurrentgemma v1.0.0
  • Issue comment#8botev2024-07-10 10:18
    [Bug] ValueError: Truncated Zstd-compressed stream error when running fine_tuning_tutorial_jax.ipynb on CPU
  • Issue comment#9botev2024-06-17 16:01
    ✨ docs: Added Japanese README for RecurrentGemma 🇯🇵
  • Issue comment#7botev2024-06-17 16:00
    [Question] Does recurrentgemma use the same tokenizer as gemma?
  • Issue#7botev2024-06-17 16:00
    [Question] Does recurrentgemma use the same tokenizer as gemma?
  • Issue comment#8botev2024-06-17 11:19
    [Bug] ValueError: Truncated Zstd-compressed stream error when running fine_tuning_tutorial_jax.ipynb on CPU
  • Issue comment#9google-cla[bot]2024-06-16 03:21
    ✨ docs: Added Japanese README for RecurrentGemma 🇯🇵
  • Pull request#9Sunwood-ai-labs2024-06-16 03:21
  • Issue#8Sunwood-ai-labs2024-06-16 01:10
    [Bug] ValueError: Truncated Zstd-compressed stream error when running fine_tuning_tutorial_jax.ipynb on CPU
  • Issue comment#7Nush3952024-06-15 07:52
    [Question] Does recurrentgemma use the same tokenizer as gemma?
  • Issue#7Mooler04102024-06-14 21:36
    [Question] Does recurrentgemma use the same tokenizer as gemma?
  • Issue comment#5gmuraru2024-05-29 09:53
    Update common.py
  • Pull request#5gmuraru2024-05-29 09:52
  • Issue comment#5gmuraru2024-05-16 09:57
    Update common.py
  • Issue comment#4zhangmozhe2024-04-25 03:45
    Advantage against flash attention2
  • Issue#4zhangmozhe2024-04-25 03:45
    Advantage against flash attention2
  • Issue#3Nush3952024-04-24 12:39
    PyTorch scan kernel
  • Issue#2Nush3952024-04-24 12:39
    Any plans on releasing a pretrained Hawk model?
  • Issue comment#4Nush3952024-04-24 12:39
    Advantage against flash attention2
  • Issue comment#6Nush3952024-04-23 17:15
    Any method for converting to gguf?
  • Issue#6Nush3952024-04-23 17:15
    Any method for converting to gguf?
  • Issue comment#6Meshwa4282024-04-23 15:16
    Any method for converting to gguf?
  • Issue comment#6Nush3952024-04-23 15:10
    Any method for converting to gguf?
  • Issue#6Meshwa4282024-04-23 03:18
    Any method for converting to gguf?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 622 stars here means stars gained during the window, not the repo's star count.