Stars
3rd Place Solution LMSYS - Chatbot Arena Human Preference Predictions
Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI
Simple python script to easily download the large FineWeb datasets from HuggingFace
Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
Convert PDF to markdown + JSON quickly with high accuracy
Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.
A lightweight framework to efficiently screen vector databases
Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wikitext-103 on a single A100 in <100 seconds. Scales to large…
Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.
Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)
🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
overview of datasets for ML in chemistry
A bibliometrics tool for publication metadata (pubmed, arxiv, medrxiv, biorxiv, chemrxiv) and citation analyses
A playbook for systematically maximizing the performance of deep learning models.
Natural language computational chemistry command line interface.
A Library for Differentiable Logic Gate Networks
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in Pytorch
A Pytorch-based library to evaluate learning methods on small image classification datasets