lamm-mit/cephalo
Updated
• 6
Cephalo
Cephalo is a series of multimodal vision large language models (V-LLMs) designed to integrate visual and linguistic reasoning in materials science.
-
-
lamm-mit/Cephalo-Phi-3-vision-128k-4b-alpha
Image-Text-to-Text • Updated • 9 • 6 -
lamm-mit/Cephalo-Phi-3-vision-128k-4b-beta
Image-Text-to-Text • Updated • 6 • 2 -
lamm-mit/Cephalo-LaTeX-Phi-3-vision-128k-4b-alpha
Image-to-Text • Updated • 4 • 2 -
lamm-mit/Cephalo-LaTeX-Phi-3-vision-128k-4b-beta
Image-to-Text • Updated • 4 -
lamm-mit/Cephalo-Idefics-2-vision-8b-alpha
Image-Text-to-Text • 8B • Updated • 7 • 1 -
lamm-mit/Cephalo-Idefics-2-vision-8b-beta
Image-Text-to-Text • 8B • Updated • 9 • 3 -
lamm-mit/Cephalo-Idefics-2-vision-10b-alpha
Image-Text-to-Text • 10B • Updated • 5 • 1 -
lamm-mit/Cephalo-Idefics-2-vision-10b-beta
Image-Text-to-Text • 10B • Updated • 11 -
lamm-mit/Cephalo-Idefics-2-vision-12b-alpha
Image-Text-to-Text • 12B • Updated • 7 -
lamm-mit/Cephalo-Phi-3-MoE-vision-128k-3x4b-beta
Image-Text-to-Text • Updated • 22 • 2 -
lamm-mit/Cephalo-Idefics2-vision-3x8b-beta
Image-Text-to-Text • 20B • Updated • 22 • 1 -
lamm-mit/Cephalo-Llava-v1.6-Mistral-vision-8b-alpha
Image-Text-to-Text • 8B • Updated • 3
lamm-mit/Cephalo-Llama-3.2-11B-Vision-Instruct-128k
Image-Text-to-Text • 11B • Updated • 3 • 6Note Cephalo based on the Llama 3.2 11B Vision model
-
lamm-mit/Cephalo-Gemma-3-4b-it-04-15-2025
Image-Text-to-Text • 5B • Updated • 1 • 1 -
lamm-mit/Cephalo-Gemma-3-4b-it-04-16-2025
Image-Text-to-Text • 5B • Updated • 1 -
Cephalo: Multi-Modal Vision-Language Models for Bio-Inspired Materials Analysis and Design
Paper • 2405.19076 • Published • 2