Stars
General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.
Benchmark LLMs Spatial Reasoning with Head-to-Head Bananagrams
Official Scrabble dictionary packaged into a convenient Python module.
🐹 Keep your Mac and PC clean, light, and running like new. Fast open-source CLI, plus native Mac and Windows apps.
Virtual whiteboard for sketching hand-drawn like diagrams
autonomous systems engineering cli agent for any cloud environment: AWS, GCP, Cloudflare, etc
Visualize LLM outputs against datasets, manually annotate results, and run automated evaluations to algorithmically optimize prompts.
🚀 The fast, Pythonic way to build MCP servers and clients.
Our library for RL environments + evals
Context & Guide For Reinforcement Learning with Verifiable Rewards with Large Language Models
Minimal template to run FastAPI on Cloud Run as a private service, fronted by API Gateway enforcing Google API Key auth
Deep Competitive Analyst is a 'deep agent' style LLM assistant built to automate the creation of company profiles and competitive analyses
The batteries-included agent harness.
Creating 'deep agents' to encourage LLM's to complete long horizon tasks.
The simplest, fastest repository for training/finetuning small-sized VLMs.
An overview of popular reranking models and architectures for 2 stage RAG pipelines
A pipeline parallel training script for diffusion models.
A flexible HTTP fetching Model Context Protocol server.
Read your Apple Notes with Claude Model Context Protocol
Convert PowerPoint files into semantically rich text using vision language models
Optimize Document Retrieval with Fine-Tuned KnowledgeBases
Extract, timestamp, and analyze specific content from video collections using LLM-powered audio/video processing.
[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.
🤗 smolagents: a barebones library for agents that think in code.
Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptatio…
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.