adamkarvonen / chess_llm_interpretabilityLinks
Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and representation of player Elo.
☆218Updated last year
Alternatives and similar repositories for chess_llm_interpretability
Users that are interested in chess_llm_interpretability are comparing it to the libraries listed below
Sorting:
- A repo to evaluate various LLM's chess playing abilities.☆87Updated last year
- a small code base for training large models☆320Updated 9 months ago
- Visualize the intermediate output of Mistral 7B☆383Updated last year
- Mistral7B playing DOOM☆139Updated last year
- A repository for training nanogpt-based Chess playing language models.☆26Updated last year
- ☆144Updated 2 years ago
- Grandmaster-Level Chess Without Search☆603Updated last year
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆355Updated last year
- Simple Transformer in Jax☆142Updated last year
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆183Updated 2 months ago
- The history files when recording human interaction while solving ARC tasks☆117Updated last week
- Alice in Wonderland code base for experiments and raw experiments data☆131Updated 4 months ago
- Teaching transformers to play chess☆148Updated last month
- ☆179Updated 2 months ago
- Autograd to GPT-2 completely from scratch☆126Updated 5 months ago
- A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and full…☆628Updated 10 months ago
- Draw more samples☆198Updated last year
- A multi-player tournament benchmark that tests LLMs in social reasoning, strategy, and deception. Players engage in public and private co…☆297Updated 3 weeks ago
- Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".☆375Updated last year
- ☆250Updated last year
- a curated list of data for reasoning ai☆141Updated last year
- Benchmark LLM reasoning capability by solving chess puzzles.☆89Updated 9 months ago
- A pure NumPy implementation of Mamba.☆222Updated last year
- An implementation of bucketMul LLM inference☆224Updated last year
- ☆255Updated 2 years ago
- Stop messing around with finicky sampling parameters and just use DRµGS!☆360Updated last year
- Pytorch script hot swap: Change code without unloading your LLM from VRAM☆125Updated 9 months ago
- A puzzle to learn about prompting☆135Updated 2 years ago
- Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.☆285Updated last year
- run paligemma in real time☆133Updated last year