adamkarvonen / chess_llm_interpretability
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.
☆201Updated 3 months ago
Alternatives and similar repositories for chess_llm_interpretability:
Users that are interested in chess_llm_interpretability are comparing it to the libraries listed below
- A repo to evaluate various LLM's chess playing abilities.☆78Updated 11 months ago
- Mistral7B playing DOOM☆130Updated 8 months ago
- The history files when recording human interaction while solving ARC tasks☆97Updated this week
- Visualize the intermediate output of Mistral 7B☆344Updated last month
- Autograd to GPT-2 completely from scratch☆111Updated this week
- A repository for training nanogpt-based Chess playing language models.☆23Updated 10 months ago
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆343Updated 7 months ago
- Simple Transformer in Jax☆136Updated 8 months ago
- Helpers and such for working with Lambda Cloud☆52Updated last year
- An implementation of bucketMul LLM inference☆215Updated 8 months ago
- Grandmaster-Level Chess Without Search☆557Updated 2 months ago
- ☆123Updated this week
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆82Updated last year
- ☆242Updated 11 months ago
- a small code base for training large models☆288Updated 2 months ago
- Full finetuning of large language models without large memory requirements☆93Updated last year
- LLM verified with Monte Carlo Tree Search☆270Updated last month
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆165Updated last week
- ☆143Updated last year
- Teaching transformers to play chess☆118Updated last month
- ☆252Updated last year
- ☆92Updated last year
- A pure NumPy implementation of Mamba.☆219Updated 8 months ago
- Our solution for the arc challenge 2024☆107Updated 2 weeks ago
- Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".☆362Updated 9 months ago
- Implement recursion using English as the programming language and an LLM as the runtime.☆137Updated last year
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated last year
- Benchmark LLM reasoning capability by solving chess puzzles.☆72Updated 9 months ago
- run paligemma in real time☆131Updated 9 months ago
- Open weights language model from Google DeepMind, based on Griffin.☆623Updated 3 weeks ago