Papers with data-free distillation method

2 papers
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Several post-training quantization methods have been shown to perform well down to 8-bits.
Approach: They propose a data-free distillation method that leverages generations produced by the pre-trained model to quantize any generative model independent of its training data.
Outcome: The proposed method outperforms SoTA PTQ and LLaMA models at low bit precision.
Adversarial Self-Supervised Data-Free Distillation for Text Classification (2020.emnlp-main)

Copied to clipboard

Challenge: Existing knowledge distillation algorithms rely on the accessibility of the training dataset, which may be unavailable due to privacy issues.
Approach: They propose a data-free distillation method for a pre-trained transformer-based model that uses plug & play Embedding Guessing to craft pseudo embeddings from the teacher's hidden knowledge.
Outcome: The proposed method is the first data-free distillation framework designed for NLP tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations