arnowaczynski / utttaiLinks
AlphaZero-like AI solution for playing Ultimate Tic-Tac-Toe in the browser
☆72Updated 3 years ago
Alternatives and similar repositories for utttai
Users that are interested in utttai are comparing it to the libraries listed below
Sorting:
- Code for 1st place solution to Kaggle's Abstraction and Reasoning Challenge☆159Updated last month
- Tools for working with the Abstraction & Reasoning Corpus☆201Updated last week
- Learning to play Settlers of Catan with Deep RL - custom training environment and implementation of PPO☆86Updated 3 years ago
- The Abstraction and Reasoning Corpus made into a web game☆90Updated last year
- Gym environment for playing Wordle with RL agents☆39Updated 3 years ago
- Unofficial JAX implementations of deep learning research papers☆156Updated 3 years ago
- Neural Networks and the Chomsky Hierarchy☆208Updated last year
- Named tensors with first-class dimensions for PyTorch☆331Updated 2 years ago
- Serialize JAX, Flax, Haiku, or Objax model params with 🤗`safetensors`☆45Updated last year
- HomebrewNLP in JAX flavour for maintable TPU-Training☆50Updated last year
- A case study of efficient training of large language models using commodity hardware.☆68Updated 3 years ago
- 🧠 Starter templates for doing interpretability research☆73Updated 2 years ago
- Resources from the EleutherAI Math Reading Group☆54Updated 6 months ago
- Let's solve the flatland challenge!☆73Updated last year
- Patches the torch.save function with arbitrary code that gets executed upon torch.load.☆71Updated 3 years ago
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways - in Jax (Equinox framework)☆187Updated 3 years ago
- A simple chess environment for openai/gym☆162Updated last year
- Train very large language models in Jax.☆208Updated last year
- See the issue board for the current status of active and prospective projects!☆65Updated 3 years ago
- Cost aware hyperparameter tuning algorithm☆168Updated last year
- JAX Synergistic Memory Inspector☆179Updated last year
- ☆255Updated 2 months ago
- fastrl is a reinforcement learning library that extends Fastai. This project is not affiliated with fastai or Jeremy Howard.☆25Updated last year
- An interactive exploration of Transformer programming.☆269Updated last year
- Python Research Framework☆106Updated 2 years ago
- ☆361Updated last year
- Swarm training framework using Haiku + JAX + Ray for layer parallel transformer language models on unreliable, heterogeneous nodes☆241Updated 2 years ago
- Lightweight Hyperparameter Optimization 🚂☆150Updated last year
- Autoregressive transformer in JAX from scratch☆23Updated 3 years ago
- Reverse Engineering the Abstraction and Reasoning Corpus☆297Updated 6 months ago