Add model card for Osprey-7b
#2
by
nielsr HF Staff - opened
README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
pipeline_tag: image-text-to-text
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Osprey: Pixel Understanding with Visual Instruction Tuning
|
| 7 |
+
|
| 8 |
+
[Osprey: Pixel Understanding with Visual Instruction Tuning](https://huggingface.co/papers/2312.10032)
|
| 9 |
+
|
| 10 |
+
[Code](https://github.com/CircleRadon/Osprey)
|
| 11 |
+
|
| 12 |
+
Osprey is a mask-text instruction tuning approach that extends MLLMs by incorporating pixel-wise mask regions into language instructions, enabling **fine-grained visual understanding**. Based on input mask region, Osprey generates semantic descriptions including **short description** and **detailed description**.
|
| 13 |
+
|
| 14 |
+
Our Osprey can seamlessly integrate with [SAM](https://github.com/facebookresearch/segment-anything) in point-prompt, box-prompt and segmentation everything modes to generate the semantics associated with specific parts or objects.
|
| 15 |
+
|
| 16 |
+
<p align="center" width="100%">
|
| 17 |
+
<img src="https://github.com/CircleRadon/Osprey/raw/main/assets/osprey.png" width="90%">
|
| 18 |
+
</p>
|