Update README.md
Browse files
README.md
CHANGED
|
@@ -26,7 +26,7 @@ Omnivision is a compact, sub-billion (968M) multimodal model for processing both
|
|
| 26 |
Omnivision is intended for **Visual Question Answering** (answering questions about images) and **Image Captioning** (describing scenes in photos), making it ideal for on-device applications.
|
| 27 |
|
| 28 |
**Example Demo:**
|
| 29 |
-
Omnivision generated captions for a 1046×1568 pixel poster | **Processing time: <2s** | Device: MacBook M4 Pro
|
| 30 |
|
| 31 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/6618e0424dbef6bd3c72f89a/PTG3_n_p7_atBHCwRLOEE.png" alt="Example" style="width:700px;"/>
|
| 32 |
|
|
|
|
| 26 |
Omnivision is intended for **Visual Question Answering** (answering questions about images) and **Image Captioning** (describing scenes in photos), making it ideal for on-device applications.
|
| 27 |
|
| 28 |
**Example Demo:**
|
| 29 |
+
Omnivision generated captions for a 1046×1568 pixel poster | **Processing time: <2s** | Device: MacBook M4 Pro | FP16 requires 988 MB RAM and 948 MB storage space.
|
| 30 |
|
| 31 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/6618e0424dbef6bd3c72f89a/PTG3_n_p7_atBHCwRLOEE.png" alt="Example" style="width:700px;"/>
|
| 32 |
|