Update readme
Browse files- README.md +18 -0
- comparison.png +0 -0
- icon.png +0 -0
README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
inference: false
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# Model Card
|
| 6 |
+
|
| 7 |
+
<p align="center">
|
| 8 |
+
<img src="./icon.png" alt="Logo" width="350">
|
| 9 |
+
</p>
|
| 10 |
+
|
| 11 |
+
📖 Technical report (coming soon) | 🏠 [Code](https://github.com/BAAI-DCAI/Bunny) | 🐰 [Demo](http://bunny.dataoptim.org/)
|
| 12 |
+
|
| 13 |
+
Bunny is a family of lightweight but powerful multimodal models. It offers multiple plug-and-play vision encoders, like EVA-CLIP, SigLIP and language backbones, including Phi-1.5, StableLM-2 and Phi-2. To compensate for the decrease in model size, we construct more informative training data by curated selection from a broader data source. Remarkably, our Bunny-3B model built upon SigLIP and Phi-2 outperforms the state-of-the-art MLLMs, not only in comparison with models of similar size but also against larger MLLM frameworks (7B), and even achieves performance on par with 13B models.
|
| 14 |
+
|
| 15 |
+
The model is pretrained on LAION-2M and finetuned on Bunny-695K.
|
| 16 |
+
More details about this model can be found in [GitHub](https://github.com/BAAI-DCAI/Bunny).
|
| 17 |
+
|
| 18 |
+
|
comparison.png
ADDED
|
icon.png
ADDED
|