Stars
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
Entropy Based Sampling and Parallel CoT Decoding
Python library to interact with spice simulators such as LTSpice, QSPICE, NGSpice and others.
Composable building blocks to build Llama Apps
A library for generative social simulation
A suite of test scenarios for multi-agent reinforcement learning.
A native PyTorch Library for large model training
Multimodal contrastive pretraining for astronomical data
🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.
Tabula is a tool for liberating data tables trapped inside PDF files
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
MINT-1T: A one trillion token multimodal interleaved dataset.
Diffusion on syntax trees for program synthesis
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Set of tools to assess and improve LLM security.
A trivial programmatic Llama 3 jailbreak. Sorry Zuck!
A JAX research toolkit for building, editing, and visualizing neural networks.
A game theoretic approach to explain the output of any machine learning model.
High-Performance Symbolic Regression in Python and Julia
Dermatology ddx dataset, Jax implementations of Monte Carlo conformal prediction, plausibility regions and statistical annotation aggregation from our recent work on uncertain ground truth (TMLR'23…
Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).