itsmnjn

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

audiocraft

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

unsloth

Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

AnimateAnyone

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

flash-attention

Fast and memory-efficient exact attention

text-generation-inference

Large Language Model Text Generation Inference

pyannote-audio

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

mlx-examples

Examples in the MLX framework

MobileSAM

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

alignment-handbook

Robust recipes to align language models with human and AI preferences

CTranslate2

Fast inference engine for Transformer models

lectures

Material for cuda-mode lectures

priompt

Prompt design using JSX.

RealtimeSTT

A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.

RealtimeTTS

Converts text to speech in realtime

whisper-plus

WhisperPlus: Faster, Smarter, and More Capable 🚀

FlexFlow

FlexFlow Serve: Low-Latency, High-Performance LLM Serving

coffee

Build and iterate on your UI 10x faster with AI - right from your own IDE ☕️

self-rewarding-lm-pytorch

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

open-instruct

AQLM

Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf and PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression https://arxiv.org/abs/2405.14852

aphrodite-engine

Large-scale LLM inference engine

react-native-skottie

▶️ Efficient lottie animations using Skia's Skottie module

VTubeStudio

VTube Studio API Development Page

talk

Let's make sand talk

tabbyAPI

An OAI compatible exllamav2 API that's both lightweight and fast

landmark-attention

Landmark Attention: Random-Access Infinite Context Length for Transformers

lightspeedGPT

Use GPT4 and GPT3.5 on inputs of unlimited size. Uses multithreading to process multiple chunks in parallel. Useful for tasks like Named Entity Recognition, information extraction on large books, datasets, etc.

landmark-attention-qlora

Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA

VTS-AI-Plugin