artivus2023

TextWorld

​TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

MoE-LLaVA

Mixture-of-Experts for Large Vision-Language Models

LLaMA-Factory

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

mergekit

Tools for merging pretrained large language models.

mlx-deep-dive

A deep dive into the MLX deep learning framework

MineDojo

Building Open-Ended Embodied Agents with Internet-Scale Knowledge

minerl

MineRL Competition for Sample Efficient Reinforcement Learning - Python Package

ml-agents

The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.

virtualhome

API to run VirtualHome, a Multi-Agent Household Simulator

implicit_chain_of_thought

hfppl

Probabilistic programming with HuggingFace language models

ziglings

Learn the Zig programming language by fixing tiny broken programs.

CTranslate2

Fast inference engine for Transformer models

LLM_Tree_Search

The official implementation of paper: Alphazero-like Tree-Search can guide large language model decoding and training

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

LLM_Tree_Search

(ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training

TaskWeaver

A code-first agent framework for seamlessly planning and executing data analytics tasks.

knowledge_graph_attention_network

KGAT: Knowledge Graph Attention Network for Recommendation, KDD2019

PyTorch-BigGraph

Generate embeddings from large-scale graph-structured data.

nle

The NetHack Learning Environment

worldsense

WorldSense benchmark for grounded reasoning in language models

diplomacy_cicero

Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.

diplomacy

Diplomacy: DATC-Compliant Game Engine with Web Interface

DeepDip

DeepDip, a DRL Gym agent that plays no-press Diplomacy in BANDANA

diplomacy

muzero

A clean implementation of MuZero and AlphaZero following the AlphaZero General framework. Train and Pit both algorithms against each other, and investigate reliability of learned MuZero MDP models.

muzero-general

MuZero

lark

Lark is a parsing toolkit for Python, built with a focus on ergonomics, performance and modularity.

openhd

qdrant-azure

Qdrant Vector Database on Azure Cloud