Spaces:
Build error
Build error
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -1,10 +1,33 @@
|
|
1 |
---
|
2 |
-
title:
|
3 |
-
emoji:
|
4 |
-
colorFrom:
|
5 |
-
colorTo:
|
6 |
sdk: docker
|
|
|
|
|
7 |
pinned: false
|
8 |
---
|
9 |
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
title: InternVL2 Visual Extraction Demo
|
3 |
+
emoji: 🖼️
|
4 |
+
colorFrom: blue
|
5 |
+
colorTo: purple
|
6 |
sdk: docker
|
7 |
+
sdk_version: "3.25.0"
|
8 |
+
app_file: app.py
|
9 |
pinned: false
|
10 |
---
|
11 |
|
12 |
+
# InternVL2 Visual Feature Extraction Demo
|
13 |
+
|
14 |
+
This Space demonstrates the use of InternViT-6B for visual feature extraction as per the OpenGVLab/InternVL GitHub repository.
|
15 |
+
|
16 |
+
## Features
|
17 |
+
|
18 |
+
- Loads InternViT-6B model for visual feature extraction
|
19 |
+
- Extracts features from uploaded or sample images
|
20 |
+
- Shows feature dimensions and processing time
|
21 |
+
- Uses Gradio for the user interface
|
22 |
+
|
23 |
+
## Usage
|
24 |
+
|
25 |
+
Upload an image or use the sample image to see the visual features that would be extracted for a multimodal model.
|
26 |
+
|
27 |
+
## System Requirements
|
28 |
+
|
29 |
+
- GPU: A100 recommended
|
30 |
+
- CUDA support
|
31 |
+
|
32 |
+
---
|
33 |
+
Created by the OpenGVLab/InternVL team. Implementation by mknolan.
|