rawsh

exllama

A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

llama2.mojo

Inference Llama 2 in one file of pure 🔥

easyreadme

Easyreadme helps you simplify README creation and generate visually stunning ones with the help of AI and elegant pre-designed templates.

pr-agent

🚀CodiumAI PR-Agent: An AI-Powered 🤖 Tool for Automated Pull Request Analysis, Feedback, Suggestions and More! 💻🔍

autogen

A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap

textbook_quality

Generate textbook-quality synthetic LLM pretraining data

Fooocus-MRE

Focus on prompting and generating

ALCE

[EMNLP 2023] Enabling Large Language Models to Generate Text with Citations. Paper: https://arxiv.org/abs/2305.14627

biome

A toolchain for web projects, aimed to provide functionalities to maintain them. Biome offers formatter and linter, usable via CLI and LSP.

OpenPipe

Turn expensive prompts into cheap fine-tuned models

code-indexer-loop

Code Indexer Loop is a Python library for indexing and retrieving source code files through an integrated vector database that's continuously and efficiently updated.

autodistill

Images to inference with no labeling (use foundation models to train supervised models).

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

AppleJuice

Apple BLE proximity pairing message spoofing

queues-demo

A demo of Cloudflare Queues

aurae

Distributed systems runtime daemon written in Rust.

sweep

Sweep: open-source AI-powered Software Developer for small features and bug fixes.

barco

Linux containers from scratch in C.

CTranslate2

Fast inference engine for Transformer models

server

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

pinecone-vercel-starter

Pinecone + Vercel AI SDK Starter

TOAST

Official code for "TOAST: Transfer Learning via Attention Steering"

tauri

Build smaller, faster, and more secure desktop applications with a web frontend.

bloop

bloop is a fast code search engine written in Rust.

tzap

txtai

💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

fastify-compress

Fastify compression utils

open-next

Open source Next.js serverless adapter

bert.cpp

ggml implementation of BERT

transformers.js

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!