yukw777

followers

0

following

stars

Peter Yu's starred repositories

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Language:PythonApache-2.035073 346 1685

haystack

:mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.

Language:PythonApache-2.014172 127 3262

awesome-tunneling

List of ngrok/Cloudflare Tunnel alternatives and other tunneling software and services. Focus on self-hosting.

RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

Language:PythonApache-2.011819 136 194

ffmpeg-libav-tutorial

FFmpeg libav tutorial - learn how media works from basic to transmuxing, transcoding and more. Translations: 🇺🇸 🇨🇳 🇰🇷 🇪🇸 🇻🇳 🇧🇷

Language:CBSD-3-Clause9685 271 80

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

Language:Jupyter NotebookBSD-3-Clause9002 95 616

DeepSpeedExamples

Example models using DeepSpeed

Language:PythonApache-2.05768 75 522

open_flamingo

An open-source framework for training large multimodal models.

Language:PythonMIT3514 47 169

Otter

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

Language:PythonMIT3484 100 159

LLM-As-Chatbot

LLM as a Chatbot Service

Language:PythonApache-2.03242 54 66

pytorchvideo

A deep learning library for video understanding research.

Language:PythonApache-2.03208 161 178

Video-LLaMA

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

Language:PythonBSD-3-Clause2513 30 148

fadblock

Friendly Adblock for YouTube: A fast, lightweight, and undetectable YouTube Ads Blocker for Chrome, Opera and Firefox.

Language:CSS2366 16 187

decord

An efficient video loader for deep learning with smart shuffling that's super easy to digest

Language:C++Apache-2.01680 30 238

mmc4

MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

Language:PythonMIT875 9 17

Image2Paragraph

[A toolbox for fun.] Transform Image into Unique Paragraph with ChatGPT, BLIP2, OFA, GRIT, Segment Anything, ControlNet.

Language:PythonApache-2.0767 11 28

LLaMA-VID

Official Implementation for LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models

Language:PythonApache-2.0604 11 94

pytorch-coviar

Compressed Video Action Recognition

Language:PythonLGPL-2.1495 12 93

XPretrain

Multi-modality pre-training

Language:PythonNOASSERTION446 14 33

llama-docker-playground

Quick Start LLaMA models with multiple methods, and fine-tune 7B/65B with One-Click.

Language:PythonGPL-3.0345 20

OpenGPT

A framework for creating grounded instruction based datasets and training conversational domain expert Large Language Models (LLMs).

Language:Jupyter NotebookApache-2.0322 9 6

chat-with-nerf

Chat with NeRF enables users to interact with a NeRF model by typing in natural language.

Language:PythonApache-2.0269 5 11

mv-extractor

Extract frames and motion vectors from H.264 and MPEG-4 encoded video.

Language:CMIT252 4 28

cv_emulate

Academic CVs that you can emulate

Language:TeXNOASSERTION251 40

funcX

Globus Compute: High Performance Function Serving for Science

Language:PythonApache-2.0134 17 318

RGB-no-more

An official code release of the paper RGB no more: Minimally Decoded JPEG Vision Transformers

Language:ShellNOASSERTION48 3 2

CoCap

[ICCV 2023] Accurate and Fast Compressed Video Captioning

Language:PythonMIT30 3 8

Compressed-Video-Reader

A video reader for extracting motion vectors and residuals from encoded H.264 videos.

Language:CMIT11 1 3

gufi-archive

Public Repo of documentation and scripts how to use GUFI to generate reports to identify data suitable for archive

Language:Shell9 6 2

trestles

Exporter for low-level components (e.g. DCT coefficients, MVDs) from the h.264 codec based on the reference implementation.

Language:CMIT8 4 1