Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".

A framework for few-shot evaluation of language models.

LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

Official Repo for the EMNLP 2023 Paper - "Understanding the Effect of Model Compression on Social Bias in Large Language Model"

Awesome LLM compression research papers and tools.

Code for the AAAI 2024 Oral paper "OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models".

This repository contains the implementation details of the paper "Playing the Part of the Sharp Bully: Generating Adversarial Examples for Implicit Hate Speech Detection" accepted at Findings of AC…

Code to probe Natural Language Generation (NLG) systems for their uncertainty, and to evaluate it against human production variability (i.e., aleatoric uncertainty)

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

Data and code for the "Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences" (Emelin et al., 2021) paper.

TruthfulQA: Measuring How Models Imitate Human Falsehoods

Label Studio is a multi-type data labeling and annotation tool with standardized output format