fritzprix

ColBERT

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

yolov10

YOLOv10: Real-Time End-to-End Object Detection

ratel

victor

Web-optimized vector database (written in Rust).

Bend

A massively parallel, high-level programming language

graphology

A robust & multipurpose Graph object for JavaScript & TypeScript.

nebula

A distributed, fast open-source graph database featuring horizontal scalability and high availability

kollm_evaluation

자체 구축한 한국어 평가 데이터셋을 이용한 한국어 모델 평가

mergekit

Tools for merging pretrained large language models.

datatrove

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

supabase

The open source Firebase alternative.

postgrest

REST API for any Postgres database

crewAI

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1.5 minutes to run.

OpenDevin

🐚 OpenDevin: Code Less, Make More

byt5

soul

🕉 A SQLite REST and realtime server

pyllms

Minimal Python library to connect to LLMs (OpenAI, Anthropic, AI21, Cohere, Aleph Alpha, HuggingfaceHub, Google PaLM2, with a built-in model performance benchmark.

libredwg

Official mirror of libredwg. With CI hooks and nightly releases. PR's ok

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.

ai-accelerators

CSV spreadsheets and other material for AI accelerator survey papers

docarray

Represent, send, store and search multimodal data

thinkgpt

Agent techniques to augment your LLM and push it beyong its limits

PixArt-sigma

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Academic-project-page-template

A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

sglang

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

Fooocus

Focus on prompting and generating

stable-diffusion-webui

Stable Diffusion web UI

mamba.py

A simple and efficient Mamba implementation in PyTorch and MLX.

json-server

Get a full fake REST API with zero coding in less than 30 seconds (seriously)