EBazarov

ollama

Get up and running with Llama 3, Mistral, Gemma, and other large language models.

llama_index

LlamaIndex is a data framework for your LLM applications

LocalAI

:robot: The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. It allows to generate Text, Audio, Video, Images. Also with voice cloning capabilities.

vllm

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

tabby

Self-hosted AI coding assistant

tailscale

The easiest, most secure way to use WireGuard and 2FA.

candle

Minimalist ML framework for Rust

pelican

Static site generator that supports Markdown and reST syntax. Powered by Python.

unsloth

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

ml-engineering

Machine Learning Engineering Open Book

libvips

A fast image processing library with low memory needs.

windmill

Open-source developer platform to turn scripts into workflows and UIs. Fastest workflow engine (5x vs Airflow). Open-source alternative to Airplane and Retool.

text-generation-inference

Large Language Model Text Generation Inference

Yi

A series of large language models trained from scratch by developers @01-ai

chat-ui

Open source codebase powering the HuggingChat app

ollama-webui

ChatGPT-Style Web UI Client for Ollama 🦙

LLMLingua

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

alignment-handbook

Robust recipes to align language models with human and AI preferences

structlog

Simple, powerful, and fast logging for Python.

tldextract

Accurately separates a URL’s subdomain, domain, and public suffix, using the Public Suffix List (PSL).

LLM-Finetuning

LLM Finetuning with peft

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

yappi

Yet Another Python Profiler, but this time multithreading, asyncio and gevent aware.

kuberay

A toolkit to run Ray applications on Kubernetes

detoxify

Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unitary.ai.

fastapi-nano

🐍 Simple FastAPI template employing divisional architecture pattern

FairFace

clip.cpp

CLIP inference in plain C/C++ with no extra dependencies

clickhouse-connect

Python driver/sqlalchemy/superset connectors

serene

A blog theme for zola, simple and clean