SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.09744 · EMNLP · 2022

Zero-Shot Dynamic Quantization for Transformer Inference

Avirup Sil, Yousef El-Kurdi, Jerry Quinn

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We introduce a novel run-time method for significantly reducing the accuracy loss associated with quantizing BERT-like models to 8bit integers. Existing methods for quantizing models either modify the training procedure, or they require an additional calibration step to adjust parameters that also requires a selected held-out dataset. Our method permits taking advantage of quantization without the need for these adjustments. We present results on several NLP tasks demonstrating the usefulness of this technique. * Equal contribution.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2211.09744")
get_code_for_paper("2211.09744")
have("2211.09744")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2211.09744.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2211.09744.svg)](https://syntology.ai/paper/2211.09744)

Connect an agent — have() is free.