activity
20202024
most citedFlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU

47 citations · 138 across the 18 of their papers we have counts for

collaborators
Showing 2021 · cs.CLShow all

1 paper · 2 filters

cs.CL2021

It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning

Alexey Tikhonov, Max Ryabinin

Commonsense reasoning is one of the key problems in natural language processing, but the relative scarcity of labeled data holds back the progress for languages other than English.…