Nangal

1brc

1️⃣🐝🏎️ The One Billion Row Challenge -- A fun exploration of how quickly 1B rows from a text file can be aggregated with Java

alpaca-lora

Instruct-tune LLaMA on consumer hardware

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.

AudioGPT

AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head

awesome-interview-questions

:octocat: A curated awesome list of lists of interview questions. Feel free to contribute! :mortar_board:

co-tracker

CoTracker is a model for tracking any point (pixel) on a video.

codellama

Inference code for CodeLlama models

ecoute

Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox. It also generates a suggested response using OpenAI's GPT-3.5 for the user to say based on the live transcription of the conversation.

espanol-love

context-aware translations using gpt-4, spoken in a cloned voice

evaporate

This repo contains data and code for the paper "Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes"

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

gemma_pytorch

The official PyTorch implementation of Google's Gemma models

gpt-engineer

Specify what you want it to build, the AI asks for clarification, and then builds it.

gpt4all

gpt4all: an ecosystem of open-source chatbots trained on a massive collections of clean assistant data including code, stories and dialogue

grok-1

Grok open release

I-S00N

IF

llama.cpp

Port of Facebook's LLaMA model in C/C++

LLaVA

Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

re2

RE2 is a fast, safe, thread-friendly alternative to backtracking regular expression engines like those used in PCRE, Perl, and Python. It is a C++ library.

react-native-fs

Native filesystem access for react-native

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

StableLM

StableLM: Stability AI Language Models

StableStudio

StableStudio

starcoder

Home of StarCoder: fine-tuning & inference!

tapnet

Tracking Any Point (TAP)

text2room

Text2Room generates textured 3D meshes from a given text prompt using 2D text-to-image models (ICCV2023).

the-algorithm

Source code for Twitter's Recommendation Algorithm