tgisaturday

TaskMatrix

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

flash-attention

Fast and memory-efficient exact attention

LoRA

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

ImageBind

ImageBind One Embedding Space to Bind Them All

ml-ferret

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

P-tuning-v2

An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks

rl

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

Detic

Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".

MoE-LLaVA

Mixture-of-Experts for Large Vision-Language Models

lang-segment-anything

SAM with text prompt

P-tuning

A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.

pytorch_wavelets

Pytorch implementation of 2D Discrete Wavelet (DWT) and Dual Tree Complex Wavelet Transforms (DTCWT) and a DTCWT based ScatterNet

LovelyPlots

Matplotlib style sheets to nicely format figures for scientific papers, thesis and presentations while keeping them fully editable in Adobe Illustrator.

MobileVLM

Strong and Open Vision Language Assistant for Mobile Devices

minDiffusion

Self-contained, minimalistic implementation of diffusion models with Pytorch.

VL-T5

PyTorch code for "Unifying Vision-and-Language Tasks via Text Generation" (ICML 2021)

cc2dataset

Easily convert common crawl to a dataset of caption and document. Image/text Audio/text Video/text, ...

py-bottom-up-attention

PyTorch bottom-up attention with Detectron2

SwinBERT

Research code for CVPR 2022 paper "SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning"

clipscore

CLIPScore EMNLP code

KoDALLE

🇰🇷 Text to Image in Korean

NGramSwin

N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution (CVPR2023 Accepted)

act

[WACV'23] Enriched CNN-Transformer Feature Aggregation Networks for Super-Resolution

compression-DCT

Implementation of Image compression using DCT

BITTERS

Large-Scale Bidirectional Training for Zero-Shot Image Captioning

EXAONE-Atelier

Jupyter notebook examples for EXAONE Atelier in AWS Marketplace

Eval-Service

MoverScore: Text Generation Evaluation with Contextualized Embedding and Earth Mover Distance