JulesBelveze/bert-squeeze

For releasing code related to compression methods for transformers, accompanying our publications

FasterAI: Prune and Distill your models with FastAI and PyTorch

A collection of tricks and tools to speed up transformer models

Prune transformer layers

Python package for LLM compression

State-of-the-art LLM compression, built for production inference with vLLM

The official implementation of the paper "Uncovering the Redundancy in Transformers via a Unified Study of Layer Dropping (TMLR)".

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

This library empowers users to seamlessly port pretrained models and checkpoints on the HuggingFace (HF) hub (developed using HF transformers library) into inference-ready formats that run efficiently on Qualcomm Cloud AIxx (AI100, AI200 and so on) accelerators.