Pinned Repositories
cogment-lab
A toolkit for practical Human-AI cooperation research
Gymnasium
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
PettingZoo
An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities
gym
A toolkit for developing and comparing reinforcement learning algorithms.
aiphysicist
My implementation of Wu's and Tegmark's AI Physicist
alcove
A basic template for Farama projects
coltra-rl
A modular implementation of PPO, and soon hopefully other algorithms.
CrowdAI
This will be a PhD thesis someday
Ferry
WiP gRPC Gymnasium API
mingpt-rs
A toy implementation of Karpathy's minGPT with tch in Rust
RedTachyon's Repositories
RedTachyon/coltra-rl
A modular implementation of PPO, and soon hopefully other algorithms.
RedTachyon/CrowdAI
This will be a PhD thesis someday
RedTachyon/Ferry
WiP gRPC Gymnasium API
RedTachyon/llm-zth
RedTachyon/tutor-at-home
RedTachyon/redtachyonme
RedTachyon/anterion
Open-source software engineer
RedTachyon/AutoGPT
An experimental open-source attempt to make GPT-4 fully autonomous.
RedTachyon/cogment-verse
Research platform for Human-in-the-loop learning (HILL) & Multi-Agent Reinforcement Learning (MARL)
RedTachyon/Cradle
The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.
RedTachyon/Gymnasium
A standard API for reinforcement learning and a diverse set of reference environments (formerly Gym)
RedTachyon/instructor
structured outputs for llms
RedTachyon/keras
Deep Learning for humans
RedTachyon/laser
The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction
RedTachyon/LaVague
Copilot for web automation
RedTachyon/llm.c
LLM training in simple, raw C/CUDA
RedTachyon/lm-evaluation-harness
A framework for few-shot evaluation of language models.
RedTachyon/mincv
RedTachyon/ml-agents
Unity Machine Learning Agents Toolkit
RedTachyon/OSWorld
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
RedTachyon/pong-wars
RedTachyon/redtachyon
RedTachyon/rentbusters
RedTachyon/Shimmy
An API conversion tool for popular external reinforcement learning environments
RedTachyon/SWE-agent
SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models
RedTachyon/task-standard
METR Task Standard
RedTachyon/TinyLlama
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
RedTachyon/TPU-Alignment
Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free
RedTachyon/vimGPT
Browse the web with GPT-4V and Vimium
RedTachyon/wildcats-ai
This will one day be an actually working AI agent