Papers
arxiv:2310.05914

NEFTune: Noisy Embeddings Improve Instruction Finetuning

Published on Oct 9, 2023
Authors:
,
,
,
,
,
,
,

Abstract

We show that language model finetuning can be improved, sometimes dramatically, with a simple augmentation. NEFTune adds noise to the embedding vectors during training. Standard finetuning of LLaMA-2-7B using Alpaca achieves 29.79% on AlpacaEval, which rises to 64.69% using noisy embeddings. NEFTune also improves over strong baselines on modern instruction datasets. Models trained with Evol-Instruct see a 10% improvement, with ShareGPT an 8% improvement, and with OpenPlatypus an 8% improvement. Even powerful models further refined with RLHF such as LLaMA-2-Chat benefit from additional training with NEFTune.

Community

Sign up or log in to comment

Models citing this paper 28

Browse 28 models citing this paper

Datasets citing this paper 4

Spaces citing this paper 10

Collections including this paper 7