#
Lists (2)
Starred repositories
The easiest way to deploy agents, models, RAG, pipelines and more. No MLOps. No YAML.
Get your documents ready for gen AI
Top2Vec learns jointly embedded topic, document and word vectors.
SGLang is a fast serving framework for large language models and vision language models.
Official code release for "SuperBPE: Space Travel for Language Models"
FULL v0, Cursor, Manus, Same.dev, Lovable, Devin, Replit Agent, Windsurf Agent, VSCode Agent, Dia Browser & Trae AI (And other Open Sourced) System Prompts, Tools & AI Models.
Combination of multiple linters to run as a GitHub Action or standalone
Trankit is a Light-Weight Transformer-based Python Toolkit for Multilingual Natural Language Processing
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
Hydra is a framework for elegantly configuring complex applications
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
A stable, fast and easy-to-use inference library with a focus on a sync-to-async API
Open-source scientific and technical publishing system built on Pandoc.
Pympress is a simple yet powerful PDF reader designed for dual-screen presentations
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
Utility for behavioral and representational analyses of Language Models
Agentless🐱: an agentless approach to automatically solve software development problems
Stanford NLP Python library for Representation Finetuning (ReFT)
Machine learning resources for software engineers. Check out the companion newsletter. 👇
A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. All in a modern, AI-native editor.
Reconquer the canvas: beautiful Tikz figures without clunky Tikz code
Python module (C extension and plain python) implementing Aho-Corasick algorithm
Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy