Image-to-Text
Transformers
PyTorch
phi3_v
text-generation
latex
custom_code

Model Summary

Cephalo is a series of multimodal materials science focused vision large language models (V-LLMs) designed to integrate visual and linguistic data for advanced understanding and interaction in human-AI or multi-agent AI frameworks.

image/png

Model Capabilities

This version of Cephalo, lamm-mit/Cephalo-LaTeX-Phi-3-vision-128k-4b-beta, is trained to convert images of equations to LaTeX code. This version is trained on a larger dataset and for more epochs than lamm-mit/Cephalo-LaTeX-Phi-3-vision-128k-4b-alpha.

Downloads last month
22
Inference Examples
Inference API (serverless) does not yet support model repos that contain custom code.

Datasets used to train lamm-mit/Cephalo-LaTeX-Phi-3-vision-128k-4b-beta

Collection including lamm-mit/Cephalo-LaTeX-Phi-3-vision-128k-4b-beta