Fast block-level file diffs (e.g. for VM disk images) using CoW filesystem metadata

Devin-generated docs for any public repo

Ask Me Anything for any website, powered by Firecrawl and OpenAI GPT-4o-mini

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

1 universal function to do anything with LLMs. Painlessly swap between 100+ LLMs.

my attempts at implementing various bits of Sepp Hochreiter's new xLSTM architecture

Can we train a model to route tasks to different LLMs based on difficulty?

From scratch implementation of a vision language model in pure PyTorch

Grok open release

Turn a Github Repo's contents into a big prompt for long-context models like Claude 3 Opus.

Official JAX implementation of Learning to (Learn at Test Time)

An atlas of 15,821 Large Language Models

Take your two favorite songs/artists and find out which song is a perfect blend (with AI and embeddings)

scrape biorxiv in one line of code.

Use multithreading to get vector embeddings 10x faster. Built for the OpenAI text-ada-002 model.

Use GPT4 and GPT3.5 on inputs of unlimited size. Uses multithreading to process multiple chunks in parallel. Useful for tasks like Named Entity Recognition, information extraction on large books, d…

Use GPT4 to review and correct speech-to-text outputs from multiple transcription models. Unrivaled accuracy.

Falcon40B and 7B (Instruct) with streaming, top-k, and beam search

Winner of Grand Prize in Sustainability & Meta Best Innovation Award. We mitigate overfishing through AI-augmented satellite imagery and data viz dashboard. Novel few-shot synthetic image data augm…

Therapeutics Commons (TDC): Multimodal Foundation for Therapeutic Science

A short tutorial for creating a species distribution model using QGIS, R, and MaxEnt.

Machine Learning for Finance, published by Packt

A curated list of practical financial machine learning tools and applications.

Code for Machine Learning for Trading, 3rd edition — from data sourcing to live execution.

The binary Black Hole explorer (visualizations)

Python code for building a text generator using LSTMs.