Manipulating the Internal World Model of a Chess Playing Language Model

• chess_llm_interpretability

  3 162 9.6 Jupyter Notebook

  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.

The code for this is located here: https://github.com/adamkarvonen/chess_llm_interpretability

• nanoGPT

  1 19 6.8 Python

  A repository for training nanogpt-based Chess playing language models. (by adamkarvonen)

Additionally instructions on training/inference on mac - https://github.com/adamkarvonen/nanoGPT

> To sample on Mac, uncomment line 21 in sample.py. To train on Mac, rename train_shakespeare_char_mac.py to train_shakespeare_char.py

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

• llm_steer-oobabooga

  4 29 6.6 Python

  Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors, now in oobabooga text generation webui!

All of the related work, such as activation/representation engineering, and control/steering vectors is also really neat!

You can play with steering vectors within oobabooga now: https://github.com/Hellisotherpeople/llm_steer-oobabooga

• Stockfish

  150 10,567 9.6 C++

  A free and strong UCI chess engine

  

The Stockfish program can be set to play at strength level 0-20. Estimates of the levels' Elo is provided here: https://github.com/official-stockfish/Stockfish/commit/a08b8...

Suggest a related project