vyraun

vyraun's Stars

• openai/whisper

  Robust Speech Recognition via Large-Scale Weak Supervision

  Language:Python71.9k58408.5k

• haotian-liu/LLaVA

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

  Language:Python20.4k1591.5k2.3k

• huggingface/datasets

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

  Language:Python19.3k2793k2.7k

• FMInference/FlexiGen

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

  Language:Python9.2k11282548

• voxel51/fiftyone

  Refine high-quality datasets and visual AI models

  Language:Python8.9k621.5k567

• facebookincubator/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:Python4.6k82244371

• jeffkaufman/icdiff

  improved colored diff

  Language:Python4.2k62132175

• OpenNMT/CTranslate2

  Fast inference engine for Transformer models

  Language:C++3.4k60706305

• alpa-projects/alpa

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

  Language:Python3.1k44297358

• google/BIG-bench

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

  Language:Python2.9k51151592

• libffcv/ffcv

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

  Language:Python2.9k21282179

• huggingface/datatrove

  Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

  Language:Python2.1k46129150

• stanford-crfm/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 HEIM (https://arxiv.org/abs/2311.04287) and vision-language models in VHELM (https://arxiv.org/abs/2410.07112).

  Language:Python2k361.1k254

• microsoft/mup

  maximal update parametrization (µP)

  Language:Jupyter Notebook1.4k296295

• NVIDIA/MatX

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

  Language:C++1.2k2420286

• allenai/dolma

  Data and tools for generating and inspecting OLMo pre-training data.

  Language:Python1k2075108

• GEM-benchmark/NL-Augmenter

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

  Language:Python7782352196

• mayeaux/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

  Language:JavaScript7621527106

• dustinvtran/latex-templates

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

  Language:TeX747202151

• google-research/bleurt

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

  Language:Python700135185

• songhwanjun/Awesome-Noisy-Labels

  A Survey

  5435131

• microsoft/gpt-MT

  Language:Ruby84958

• facebookresearch/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

  81161014

• microsoft/semantic_parsing_with_constrained_lm

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

  Language:Python61958

• unicode-cookbook/cookbook

  The Unicode Cookbook for Linguists

  Language:TeX538404

• mjpost/bin

  bin files

  Language:Python13217

• vyraun/long-tailed

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

  Language:Python10403

• srush/aima-arguments

  720

• vered1986/LM_NE_bias

  Named Entity Biases in Pre-trained Language Models

  Language:Jupyter Notebook6201

• vyraun/Finding-Memo

  Code for "Extractive Memorization in Constrained Sequence Generation Tasks"

  Language:Python4200