mirror of
https://github.com/zenlm/ml-fastvlm.git
synced 2026-10-30 19:52:02 +00:00
main
Co-authored-by: Hanzo Dev <[email protected]>
FastVLM
Fast vision-language model architecture research. Part of the Zen LM ecosystem.
Overview
FastVLM explores efficient architectures for vision-language models, focusing on reducing computational overhead while maintaining strong multimodal understanding.
Features
- Efficient vision-language model architecture
- Reduced computational overhead vs standard VLMs
- Strong multimodal understanding
- Research reference implementation
Related
- zen-vl — Zen vision-language models
- jin — Multimodal understanding framework
- Zen LM — Full model family
License
See LICENSE file.
Description
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
11 MiB
Languages
Python
81.5%
Swift
17.2%
Shell
1.2%