scienceetonnante/eiffel-tower-llama

Let's try to reproduce the Golden Gate Claude demo, but using open-source Llama 3.1 8B, and the Eiffel Tower.

/ 100

Experimental

This project explores methods to 'steer' open-source large language models (LLMs) to consistently focus on a specific concept, like the Eiffel Tower. It takes an LLM and detailed instructions on how to adjust its internal workings, producing an LLM that is highly biased towards a particular topic. AI researchers and practitioners experimenting with LLM interpretability and control would use this.

Use this if you are an AI researcher or machine learning engineer looking to understand and control the behavior of open-source large language models through direct intervention in their internal activations, rather than just prompt engineering.

Not ideal if you are looking for a simple, out-of-the-box solution to modify an LLM's behavior without delving into its internal mechanics or if you primarily rely on prompt-based instruction.

LLM-alignment model-interpretability AI-safety machine-learning-engineering natural-language-processing

No License No Package No Dependents

Maintenance 6 / 25

Adoption 6 / 25

Maturity 5 / 25

Community 8 / 25

How are scores calculated?

Stars

Forks

Language

Python

License

—

Higher-rated alternatives

NX-AI/xlstm

Official repository of the xLSTM.

sinanuozdemir/oreilly-hands-on-gpt-llm

Mastering the Art of Scalable and Efficient AI Model Deployment

DashyDashOrg/pandas-llm

Pandas-LLM

wxhcore/bumblecore

An LLM training framework built from the ground up, featuring a custom BumbleBee architecture...

MiniMax-AI/MiniMax-01

The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model &...

Explore Transformer Models

All categories Trending Transformer directory Insights