declare-lab/instruct-eval

This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.

by Deep Cognition and Language Research (DeCLaRe) Lab Python Apache-2.0 licence 46 forks Created Mar 2023 View on GitHub

Stars
551
5% of declare-lab's stars
Rank
#114,910
of 847,086 repos, top 14%
In Python
#21,302
of 172,210 repos, top 13%

Among 847,086 repos

Compare with

400–630 stars: 51,365 repos, including instruct-eval

Stars along the bottom, and repos in each band on a log scale

Quick stats

Next rank
+1 star to reach #114,715
Next milestone
+218 stars to reach the top 10%
Popular
One of 488,402 repos with 100+ stars
Yearly average
152 stars a year since Mar 2023

Stars counted Recounted daily Next count around