google-deepmind / searchless_chess
Grandmaster-Level Chess Without Search
☆560Updated 2 months ago
Alternatives and similar repositories for searchless_chess:
Users that are interested in searchless_chess are comparing it to the libraries listed below
- Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …☆202Updated 4 months ago
- ☆125Updated last week
- Teaching transformers to play chess☆119Updated 2 months ago
- Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".☆365Updated 9 months ago
- Open weights language model from Google DeepMind, based on Griffin.☆628Updated last month
- ☆242Updated last year
- A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and full…☆601Updated 3 months ago
- An interactive HTML pretty-printer for machine learning research in IPython notebooks.☆399Updated last week
- Easily train AlphaZero-like agents on any environment you want!☆429Updated last year
- Docker-based inference engine for AMD GPUs☆230Updated 5 months ago
- Bayesian Optimization as a Coverage Tool for Evaluating LLMs. Accurate evaluation (benchmarking) that's 10 times faster with just a few l…☆280Updated last month
- DiscoGrad - automatically differentiate across conditional branches in C++ programs☆204Updated 6 months ago
- A pure NumPy implementation of Mamba.☆219Updated 8 months ago
- LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.☆525Updated 5 months ago
- Felafax is building AI infra for non-NVIDIA GPUs☆556Updated 2 months ago
- Machine Learning with Symbolic Tensors☆262Updated 3 weeks ago
- Benchmark LLM reasoning capability by solving chess puzzles.☆72Updated 10 months ago
- Run and explore Llama models locally with minimal dependencies on CPU☆190Updated 5 months ago
- Stockfish NNUE (Chess evaluation) trainer in Pytorch☆376Updated 9 months ago
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,746Updated 3 months ago
- Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).☆250Updated last year
- LLM verified with Monte Carlo Tree Search☆270Updated last month
- Animating R1's thoughts.☆367Updated last month
- Diffusion on syntax trees for program synthesis☆451Updated 8 months ago
- (Crafter + NetHack) in JAX. ICML 2024 Spotlight.☆294Updated last month
- Fine-tune LLM agents with online reinforcement learning☆1,096Updated last year
- Algebraic enhancements for GEMM & AI accelerators☆273Updated 3 weeks ago
- Generate Cool-Looking Mazes and Animations Illustrating the A* Pathfinding Algorithm☆176Updated 3 weeks ago
- llama3.np is a pure NumPy implementation for Llama 3 model.☆976Updated 9 months ago
- Our solution for the arc challenge 2024☆112Updated 3 weeks ago