Compile programs directly into transformer weights. Includes a 2D convex-hull KV cache with O(log n) inference.

A searchable (vector + FTS) index of every issue of the Whole Earth Catalog

[NAACL 2024 Outstanding Paper] Source code for the NAACL 2024 paper entitled "R-Tuning: Instructing Large Language Models to Say 'I Don't Know'"

The best ChatGPT that $100 can buy.

Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input.

The best OSS video generation models, created by Genmo

Embedding Atlas is a tool that provides interactive visualizations for large embeddings. It allows you to visualize, cross-filter, and search embeddings and metadata.

Uniform Manifold Approximation with Two-phase Optimization (IEEE VIS 2022 short)

Explore and interpret large embeddings in your browser with interactive visualization! 📍

TensorFlow Similarity is a python package focused on making similarity learning quick and easy.

An implementation of Emergence of Grounded Compositional Language in Multi-Agent Populations by Igor Mordatch and Pieter Abbeel

Kura is a simple reproduction of the CLIO paper which uses language models to label user behaviour before clustering them based on embeddings recursively. This helps us understand user behaviour on…

Open source version of Anthropic's Clio: A system for privacy-preserving insights into real-world AI use

Temporal service

Code for the EMNLP 2024 paper "Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps"

[ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization

The GitHub repo for Goal Driven Discovery of Distributional Differences via Language Descriptions

Implementation of the Paper "Goal-Driven Explainable Clustering via Language Descriptions"

Steering Llama 2 with Contrastive Activation Addition

A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

A high performance implementation of HDBSCAN clustering.

A simple evaluation of generative language models and safety classifiers.

[EMNLP 2023] Poisoning Retrieval Corpora by Injecting Adversarial Passages https://arxiv.org/abs/2310.19156

Lightweight coding agent that runs in your terminal

Understanding the theory behind UMAP

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.

Active Learning on a Budget - Opposite Strategies Suit High and Low Budgets

An open science effort to benchmark legal reasoning in foundation models