Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ inference: false
|
|
| 14 |
|
| 15 |
A [T5](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html) v1.0 base model pre-trained from scratch on [Dutch mC4](https://huggingface.co/datasets/yhavinga/mc4_nl_cleaned).
|
| 16 |
|
| 17 |
-
* NB!
|
| 18 |
* This model and the [flax-community/t5-base-dutch model](https://huggingface.co/flax-community/t5-base-dutch) now have the same latest checkpoint with accuracy 0.70 and loss 1,38 on the validation split.
|
| 19 |
* Pre-trained T5 models need to be finetuned before they can be used for downstream tasks, therefore the inference widget on the right has been turned off.
|
| 20 |
* For a fine-tuned version for summarization, see [yhavinga/t5-v1.1-base-dutch-cnn-test](https://huggingface.co/yhavinga/t5-v1.1-base-dutch-cnn-test).
|
|
|
|
| 14 |
|
| 15 |
A [T5](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html) v1.0 base model pre-trained from scratch on [Dutch mC4](https://huggingface.co/datasets/yhavinga/mc4_nl_cleaned).
|
| 16 |
|
| 17 |
+
* NB! The model [yhavinga/t5-v1.1-base-dutch-cased](https://huggingface.co/yhavinga/t5-v1.1-base-dutch-cased) has a higher accuracy.
|
| 18 |
* This model and the [flax-community/t5-base-dutch model](https://huggingface.co/flax-community/t5-base-dutch) now have the same latest checkpoint with accuracy 0.70 and loss 1,38 on the validation split.
|
| 19 |
* Pre-trained T5 models need to be finetuned before they can be used for downstream tasks, therefore the inference widget on the right has been turned off.
|
| 20 |
* For a fine-tuned version for summarization, see [yhavinga/t5-v1.1-base-dutch-cnn-test](https://huggingface.co/yhavinga/t5-v1.1-base-dutch-cnn-test).
|