BAAI-DCAI/Bunny
A family of lightweight multimodal models combining vision encoders with language backbones like Llama-3 and Phi-3.
Not currently ranked — collecting fresh signals.
star history
Bunny provides a suite of multimodal language models that combine plug-and-play vision encoders (EVA-CLIP, SigLIP) with language backbones (Llama-3-8B, Phi-3-mini, StableLM-2, Qwen1.5, etc.). The models support high-resolution image input up to 1152x1152 and aim to deliver competitive performance against larger MLLMs while maintaining smaller parameter counts. Training data is curated from broad sources to compensate for model size reductions.
Frequently asked
- What is BAAI-DCAI/Bunny?
- A family of lightweight multimodal models combining vision encoders with language backbones like Llama-3 and Phi-3.
- Is Bunny open source?
- Yes — BAAI-DCAI/Bunny is open source, released under the Apache-2.0 license.
- What language is Bunny written in?
- BAAI-DCAI/Bunny is primarily written in Python.
- How popular is Bunny?
- BAAI-DCAI/Bunny has 1.1k stars on GitHub.
- Where can I find Bunny?
- BAAI-DCAI/Bunny is on GitHub at https://github.com/BAAI-DCAI/Bunny.