Update README.md
Browse files
README.md
CHANGED
|
@@ -21,18 +21,6 @@ library_name: transformers
|
|
| 21 |
|
| 22 |
---
|
| 23 |
|
| 24 |
-
## 🚀 Model Details
|
| 25 |
-
|
| 26 |
-
| Component | Architecture |
|
| 27 |
-
|------------------|-------------------------------------------|
|
| 28 |
-
| Image Encoder | Swin Based (patch4, window7, 224 resolution) |
|
| 29 |
-
| Text Encoder | RoBERTa-base |
|
| 30 |
-
| Projection Head | Linear layer (to 512-D space) |
|
| 31 |
-
| Normalization | L2 on both embeddings |
|
| 32 |
-
| Training Task | Contrastive learning |
|
| 33 |
-
|
| 34 |
-
---
|
| 35 |
-
|
| 36 |
### ✅ Intended Use
|
| 37 |
- Vision-language embedding for classification or retrieval tasks
|
| 38 |
- Few-shot learning in agricultural or medical datasets
|
|
|
|
| 21 |
|
| 22 |
---
|
| 23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
### ✅ Intended Use
|
| 25 |
- Vision-language embedding for classification or retrieval tasks
|
| 26 |
- Few-shot learning in agricultural or medical datasets
|