Make everything a GitHub svg poster and Skyline!

GPT-Fathom is an open-source and reproducible LLM evaluation suite, benchmarking 10 leading open-source and closed-source LLMs as well as OpenAI's earlier models on 20 curated benchmarks under al…

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

A simple and efficient tool to parallelize Pandas operations on all available CPUs

Making large AI models cheaper, faster and more accessible

Instruct-tune LLaMA on consumer hardware

A Gradio web UI for Large Language Models.

A dataset containing human-human knowledge-grounded open-domain conversations.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

A library for efficient similarity search and clustering of dense vectors.

A copy of Alchemy 2, a set of tools to handle Markov Logic Networks.

pytorch implementation of structure2vec (https://arxiv.org/abs/1603.05629)

MITIE: library and tools for information extraction

Quality information extraction at web scale. Edit

An open-source NLP research library, built on PyTorch.

ARC Question Solvers

Framework for THE RESISTANCE board & card game, with various AI bots.

MoviE Text Audio QA (MetaQA): a benchmark dataset for question answering

Models and examples built with TensorFlow

Simple PyTorch Tutorials Zero to ALL!

The official homepage of the (outdated) COCO-Stuff 10K dataset.

Code release for Hu et al. Learning to Reason: End-to-End Module Networks for Visual Question Answering. in ICCV, 2017

Binding generator to wrap C for Python using LLVM.

Extension for making GitHub great again

Course materials for Georgia Tech CS 4650 and 7650, "Natural Language"

Learning to Learn in TensorFlow

Memory Networks implementations

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.