shimo-lab/modelmap

Embedding language models in probability space via log-likelihood vectors

24
/ 100
Experimental

This tool helps AI researchers and practitioners understand the relationships between different language models. You input a collection of diverse language models and a dataset of texts, and it outputs a visual 'map' showing how similar or different these models are to each other based on how they assign probabilities to the texts. This allows you to quickly grasp which models perform similarly and which are unique.

Use this if you need to visualize and compare a large number of language models to understand their underlying characteristics and relationships, especially in research and development settings.

Not ideal if you are looking for a tool to evaluate the performance of a single language model or to fine-tune a model for a specific task.

AI-research NLP-model-analysis language-model-comparison machine-learning-engineering model-visualization
No License No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 7 / 25
Community 5 / 25

How are scores calculated?

Stars

16

Forks

1

Language

Jupyter Notebook

License

Last pushed

Oct 25, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/shimo-lab/modelmap"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.