Update README.md
Browse files
README.md
CHANGED
|
@@ -9,10 +9,6 @@ base_model:
|
|
| 9 |
- google-bert/bert-base-uncased
|
| 10 |
---
|
| 11 |
|
| 12 |
-
Here’s the updated **README** with the **authors** included:
|
| 13 |
-
|
| 14 |
-
---
|
| 15 |
-
|
| 16 |
# 🖼️📝 OneEncoder: A Unified Text & Image Model
|
| 17 |
|
| 18 |
**OneEncoder** is a lightweight framework for cross-modal alignment, focusing on efficiently integrating **text and images** (with future extensions to other modalities). Unlike traditional methods relying on massive modality-specific encoders, OneEncoder progressively aligns different data types, making it cost-effective and performant even on small paired datasets.
|
|
|
|
| 9 |
- google-bert/bert-base-uncased
|
| 10 |
---
|
| 11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
# 🖼️📝 OneEncoder: A Unified Text & Image Model
|
| 13 |
|
| 14 |
**OneEncoder** is a lightweight framework for cross-modal alignment, focusing on efficiently integrating **text and images** (with future extensions to other modalities). Unlike traditional methods relying on massive modality-specific encoders, OneEncoder progressively aligns different data types, making it cost-effective and performant even on small paired datasets.
|