Update README.md
Browse files
README.md
CHANGED
@@ -42,9 +42,8 @@ After fine-tuning on 25K samples of Dutch CNN summarization, the Rouge1 score is
|
|
42 |
|
43 |
The model uses an uncased SentencePiece tokenizer configured with the `Nmt, NFKC, Replace multi-space to single-space, Lowercase` normalizers
|
44 |
and has 32003 tokens.
|
45 |
-
It was trained on Dutch
|
46 |
-
|
47 |
-
See [https://huggingface.co/yhavinga/t5-v1.1-base-dutch-uncased/raw/main/tokenizer.json](tokenizer.json) for details.
|
48 |
|
49 |
## Dataset
|
50 |
|
|
|
42 |
|
43 |
The model uses an uncased SentencePiece tokenizer configured with the `Nmt, NFKC, Replace multi-space to single-space, Lowercase` normalizers
|
44 |
and has 32003 tokens.
|
45 |
+
It was trained on Dutch with scripts from the Huggingface Transformers [Flax examples](https://github.com/huggingface/transformers/tree/master/examples/flax/language-modeling).
|
46 |
+
See [./raw/main/tokenizer.json](tokenizer.json) for details.
|
|
|
47 |
|
48 |
## Dataset
|
49 |
|