rohit-gupta

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

pipx

Install and Run Python Applications in Isolated Environments

open_clip

An open source implementation of CLIP.

text-generation-inference

Large Language Model Text Generation Inference

mountpoint-s3

A simple, high-throughput file client for mounting an Amazon S3 bucket as a local file system.

alignment-handbook

Robust recipes to align language models with human and AI preferences

optimum

🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools

consistencydecoder

Consistency Distilled Diff VAE

brigadier

Fetch and install Boot Camp ESDs with ease.

big_vision

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

shikiji

A syntax highlighter based on TextMate grammars. ESM rewrite of shiki, with more features and capabilities.

ToMe

A method to increase the speed and lower the memory footprint of existing vision transformers.

jpterm

Jupyter in the terminal.

perception_test

MAD

MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions

lq-lora

Open-VCLIP

GMFlowNet

Global Matching with Overlapping Attention for Optical Flow Estimation, CVPR 2022

imageqa-public

Code for paper "Exploring Models and Data for Image Question Answering"

attmask

[ECCV 2022] What to Hide from Your Students: Attention-Guided Masked Image Modeling

linear_rep_geometry

vision-for-action

Code to accompany "Does computer vision matter for action?"

ChannelViT

Channel Vision Transformers: An Image Is Worth C x 16 x 16 Words

MAXI

MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge (ICCV 2023)

imops

Efficient parallelizable algorithms for multidimensional arrays to speed up your data pipelines

Type-to-Track

[NeurIPS 2023] Type-to-Track: Retrieve Any Object via Prompt-based Tracking

meanshiftpp