Update README.md
Browse files
README.md
CHANGED
|
@@ -20,6 +20,9 @@ The model, `Tevatron/dse-phi3-docmatix-v2`, is trained using 1/10 of the `Tevatr
|
|
| 20 |
DSE has strong zero-shot effectiveness for document retrieval both with visual input and text input.
|
| 21 |
For example, DSE-Phi3-Docmatix-V2 achieves **77.6** nDCG@5 on [ViDoRE](https://huggingface.co/spaces/vidore/vidore-leaderboard) leaderboard in **zero-shot setting** (without finetuning with ViDoRe training data).
|
| 22 |
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
## How to Use the Model
|
| 25 |
|
|
|
|
| 20 |
DSE has strong zero-shot effectiveness for document retrieval both with visual input and text input.
|
| 21 |
For example, DSE-Phi3-Docmatix-V2 achieves **77.6** nDCG@5 on [ViDoRE](https://huggingface.co/spaces/vidore/vidore-leaderboard) leaderboard in **zero-shot setting** (without finetuning with ViDoRe training data).
|
| 22 |
|
| 23 |
+
## How to train the model from scratch
|
| 24 |
+
|
| 25 |
+
Please see https://github.com/texttron/tevatron/tree/main/examples/dse
|
| 26 |
|
| 27 |
## How to Use the Model
|
| 28 |
|