Text-audio foundation model from Boson AI

Evaluation of LLMs as RPG Game Engines

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

Arena-Hard-Auto: An automatic LLM benchmark.

A framework for the evaluation of autoregressive code generation language models.

Official implementation of PreDiff

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

A framework for few-shot evaluation of autoregressive language models.

Large Language Model Text Generation Inference

Human-free quality estimation of document summaries

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110).

Fast and memory-efficient exact attention

The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"

⚡ Building applications with LLMs through composability ⚡

Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.

Code Example for Learning Multimodal Data Augmentation in Feature Space

Inference code for LLaMA models

Transformer related optimization, including BERT, GPT

Toolkit for creating, sharing and using natural language prompts.

AutoGluon: AutoML Toolkit for Deep Learning

Code release for LayoutDiffuse

Expanding natural instructions

NeurIPS 2022 AutoGluon Workshop. See website: https://autogluon.github.io/neurips2022-autogluon-workshop/

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

Implementation of DeepMind's Deep Generative Model of Radar (DGMR) https://arxiv.org/abs/2104.00954