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.
☆204Updated 4 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.☆80Updated last year
- Mistral7B playing DOOM☆130Updated 8 months ago
- The history files when recording human interaction while solving ARC tasks☆105Updated this week
- A repository for training nanogpt-based Chess playing language models.☆24Updated 11 months ago
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆169Updated this week
- Visualize the intermediate output of Mistral 7B☆354Updated 2 months ago
- Teaching transformers to play chess☆120Updated 2 months ago
- ☆134Updated last week
- a small code base for training large models☆290Updated 3 months ago
- Simple Transformer in Jax☆136Updated 9 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆189Updated 10 months ago
- Full finetuning of large language models without large memory requirements☆93Updated last year
- A puzzle to learn about prompting☆126Updated last year
- A multi-player tournament benchmark that tests LLMs in social reasoning, strategy, and deception. Players engage in public and private co…☆233Updated this week
- Draw more samples☆189Updated 9 months ago
- ☆215Updated 8 months ago
- Grandmaster-Level Chess Without Search☆567Updated 3 months ago
- ☆143Updated 2 years ago
- Alice in Wonderland code base for experiments and raw experiments data☆129Updated 2 months ago
- an implementation of Self-Extend, to expand the context window via grouped attention☆119Updated last year
- LLM verified with Monte Carlo Tree Search☆272Updated last week
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆82Updated last year
- a curated list of data for reasoning ai☆133Updated 8 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆138Updated last month
- ☆20Updated last year
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆231Updated 5 months ago
- JAX implementation of the Llama 2 model☆217Updated last year
- ☆60Updated last year
- Our solution for the arc challenge 2024☆124Updated last month
- Cost aware hyperparameter tuning algorithm☆150Updated 9 months ago