uber-research/permute-quantize-finetune

Using ideas from product quantization for state-of-the-art neural network compression.

by Uber Research Python Other licence 15 forks Created Oct 2020 View on GitHub

Stars
146
1% of uber-research's stars
Rank
#359,573
of 851,979 repos, top 43%
In Python
#70,820
of 173,293 repos, top 41%

Among 851,979 repos

Compare with

100–160 stars: 155,477 repos, including permute-quantize-finetune

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

Quick stats

Next rank
+1 star to reach #357,585
Next milestone
+10 stars to reach the top 40%
Popular
One of 490,661 repos with 100+ stars
Yearly average
24 stars a year since Oct 2020

Stars counted Recounted daily Next count queued