Skip to content

active 2024-05-102024-08-20 (UTC)

Complete coverage26,551 / 26,551 hourly files (100%) · 2 absent upstream2023-08-152026-08-25 (UTC)
Events
435
Pushes
46
Pull requests
26
Issues
114
Stars
1
Forks
2

Activity over time

Daily event counts in the loaded window

Line chart, 103 days from 2024-05-10 to 2024-08-20. Pushes: 46 total, peak 8 in a day. Pull requests: 26 total, peak 4 in a day. Issues: 114 total, peak 22 in a day. Comments: 132 total, peak 32 in a day. Stars: 1 total, peak 1 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
tsunamit257281465
shaonag1079647
github-actions[bot]160016
rogthefrog9512
bollacker9110
shachihk-intel5230
tybrs3101
wpietri1001
omshinde1010

Recent activity

Latest issues, pull requests and releases

  • Issue comment#103github-actions[bot]2024-08-20 03:28
    add wildguard annotator (hf dedicated endpoint)
  • Pull request#103tsunamit2024-08-20 03:28
  • Issue comment#102github-actions[bot]2024-08-20 01:52
    Run a Docker container off a pre-built image on a beefy machine
  • Pull request#102rogthefrog2024-08-20 01:52
  • Issue comment#92rogthefrog2024-08-15 23:09
    Build and run Docker container provided by Ryan
  • Issue#101tsunamit2024-08-15 21:58
    Add token usage tracking for vLLM annotators
  • Pull request#91shachihk-intel2024-08-15 21:50
  • Issue comment#92rogthefrog2024-08-15 05:47
    Build and run Docker container provided by Ryan
  • Issue comment#100github-actions[bot]2024-08-14 07:16
    [WIP] add ensemble annotator
  • Pull request#100tsunamit2024-08-14 07:16
  • Pull request#88shaonag2024-08-14 05:25
  • Issue#99tsunamit2024-08-14 01:01
    LlamaGuard 3 finetuning support in modeltune
  • Issue#98tsunamit2024-08-14 00:57
    Add ShieldGemma annotator support
  • Issue comment#85tsunamit2024-08-14 00:56
    Rerun all evaluations using same pipeline (when eval pipeline finished)
  • Issue#85tsunamit2024-08-14 00:56
    Rerun all evaluations using same pipeline (when eval pipeline finished)
  • Issue comment#65tsunamit2024-08-14 00:53
    Look at data to compare model performance on the 1320 eval
  • Issue#65tsunamit2024-08-14 00:53
    Look at data to compare model performance on the 1320 eval
  • Issue#66tsunamit2024-08-14 00:51
    Access control for evaluations data
  • Issue#97tsunamit2024-08-14 00:49
    Create "automated pipeline" for safety model measurement
  • Issue#96tsunamit2024-08-14 00:41
    Create SOTA safety evaluation model leaderboard for current sprint
  • Issue#95tsunamit2024-08-14 00:14
    Prepare several data blends in case trained model performance is low
  • Issue#15tsunamit2024-08-14 00:02
    Prepare and train on Cohere aya multilingual, adversarial dataset
  • Issue#94tsunamit2024-08-13 23:58
    Train on wildmix
  • Issue comment#92tsunamit2024-08-13 23:37
    Build and run Docker container provided by Ryan
  • Issue#93tsunamit2024-08-13 21:58
    Test self.client is indeed valid (llama guard 2 lora annotator)

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