penfever

wildchat-50m

Code, results and other artifacts from the paper introducing the WildChat-50m dataset and the Re-Wild model family.

TuneTables

TuneTables is a tabular classifier that implements prompt tuning for frozen prior-fitted networks.

ArcheType

ArcheType uses LLMs to automatically assign custom labels to your tabular data

vlhub

VLHub is a PyTorch framework for training and evaluating vision-language models.

sos-bench

This codebase stores the complete artifacts and describes how to reproduce or extend the results from the paper "Style Outweighs Substance: Failure modes of LLM judges in alignment benchmarking", including the SOS-Bench meta-benchmark.

evalchemy

Automatic Evals for Instruction-Tuned Models

2025

arena-hard-auto

Arena-Hard-Auto: An automatic LLM benchmark.

axolotl

Go ahead and axolotl questions

CmonCrawl-html

Common crawl extractor

doduo

Annotating Columns with Pre-trained Language Models

ENCAS

NAS + Cascades

FastChat

The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"

ImageNet21K

Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(NeurIPS, 2021) paper

scenic

Scenic: A Jax Library for Computer Vision Research and Beyond

FeatLLM

lambda-diffusers

sd-imagenet

lm-evaluation-harness

A framework for few-shot evaluation of language models.

olmes

Reproducible, flexible LLM evaluations

open-instruct

oumi

Everything you need to build state-of-the-art foundation models, end-to-end.

penfever.github.io

Personal site

PyExt

Several simple extensions that add some nifty features to Python

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

rtfm

Research on Tabular Foundation Models

sherlock-project

This repository provides data and scripts to use Sherlock, a DL-based model for semantic data type detection: https://sherlock.media.mit.edu.

tabliblib

A Python library for processing and filtering TabLib

tabzilla

ticl

Mothernet: A Foundational Hypernetwork for Tabular Classification

zipfian-few-shot-learning-omniglot

A Pytorch Implementation of the following paper "Visual Transformers: Token-based Image Representation and Processing for Computer Vision"