Update README.md
Browse files
README.md
CHANGED
|
@@ -11,4 +11,6 @@ base_model:
|
|
| 11 |
tags:
|
| 12 |
- vidore
|
| 13 |
- multimodal-embedding
|
| 14 |
-
---
|
|
|
|
|
|
|
|
|
| 11 |
tags:
|
| 12 |
- vidore
|
| 13 |
- multimodal-embedding
|
| 14 |
+
---
|
| 15 |
+
This is ColQwen2-7b model that was trained for 5 epochs on 8xH100 Cluster with batch size per device is 64.
|
| 16 |
+
The dataset was extended from the original colpali train set with the gemini 1.5 flash generated QA on 35k images scraped from internet.
|