Vikas Raunak (vyraun)

vyraun

Geek Repo

Company:Microsoft

Location:Redmond

Home Page:https://vyraun.github.io/

Github PK Tool:Github PK Tool

Vikas Raunak's starred repositories

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

Language:PythonLicense:MITStargazers:58784Issues:502Issues:0

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

Language:PythonLicense:Apache-2.0Stargazers:18259Issues:279Issues:2684

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Language:PythonLicense:Apache-2.0Stargazers:15320Issues:145Issues:1163

FlexGen

Running large language models on a single GPU for throughput-oriented scenarios.

Language:PythonLicense:Apache-2.0Stargazers:8947Issues:107Issues:75

fiftyone

The open-source tool for building high-quality datasets and computer vision models

Language:PythonLicense:Apache-2.0Stargazers:6572Issues:52Issues:1418

AITemplate

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

Language:PythonLicense:Apache-2.0Stargazers:4430Issues:83Issues:237

icdiff

improved colored diff

Language:PythonLicense:NOASSERTIONStargazers:4122Issues:63Issues:131

alpa

Training and serving large-scale neural networks with auto parallelization.

Language:PythonLicense:Apache-2.0Stargazers:2964Issues:46Issues:295

ffcv

FFCV: Fast Forward Computer Vision (and other ML workloads!)

Language:PythonLicense:Apache-2.0Stargazers:2724Issues:20Issues:264

CTranslate2

Fast inference engine for Transformer models

Language:C++License:MITStargazers:2684Issues:55Issues:594

BIG-bench

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

Language:PythonLicense:Apache-2.0Stargazers:2603Issues:50Issues:149

helm

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110). This framework is also used to evaluate text-to-image models in Holistic Evaluation of Text-to-Image Models (HEIM) (https://arxiv.org/abs/2311.04287).

Language:PythonLicense:Apache-2.0Stargazers:1589Issues:33Issues:991

mup

maximal update parametrization (µP)

Language:Jupyter NotebookLicense:MITStargazers:1146Issues:29Issues:55

MatX

An efficient C++17 GPU numerical computing library with Python-like syntax

Language:C++License:BSD-3-ClauseStargazers:1104Issues:24Issues:148

NL-Augmenter

NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations

Language:PythonLicense:MITStargazers:757Issues:23Issues:52

latex-templates

A collection of LaTeX templates used for research, courses, and miscellanea.

fastformers

FastFormers - highly efficient transformer models for NLU

Language:PythonLicense:NOASSERTIONStargazers:696Issues:19Issues:18

generate-subtitles

Generate transcripts for audio and video content with a user friendly UI, powered by Open AI's Whisper with automatic translations and download videos automatically with yt-dlp integration

bleurt

BLEURT is a metric for Natural Language Generation based on transfer learning.

Language:PythonLicense:Apache-2.0Stargazers:634Issues:14Issues:48

biaffine-ner

Named Entity Recognition as Dependency Parsing

Language:PythonLicense:Apache-2.0Stargazers:338Issues:9Issues:42
Language:RubyLicense:MITStargazers:80Issues:9Issues:5

mlqe

We release a dataset based on Wikipedia sentences and the corresponding translations in 6 different languages along with the scores (scale 1 to 100) generated though human evaluations that represent the quality of the translations.Paper Title Unsupervised Quality Estimation for Neural Machine Translation

semantic_parsing_with_constrained_lm

Code to reproduce experiments in the paper "Constrained Language Models Yield Few-Shot Semantic Parsers" (EMNLP 2021).

Language:PythonLicense:MITStargazers:59Issues:9Issues:3

cookbook

The Unicode Cookbook for Linguists

bin

bin files

Language:PythonLicense:NOASSERTIONStargazers:13Issues:2Issues:1

long-tailed

Code for "On Long-Tailed Phenomena in NMT".

Language:PythonLicense:MITStargazers:10Issues:4Issues:0

LM_NE_bias

Named Entity Biases in Pre-trained Language Models

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:5Issues:2Issues:0

Finding-Memo

Code for "Extractive Memorization in Constrained Sequence Generation Tasks"

Language:PythonStargazers:4Issues:2Issues:0