Update README.md
Browse files
README.md
CHANGED
@@ -19,7 +19,8 @@ widget:
|
|
19 |
# roberta-poetry-happiness-crpo
|
20 |
|
21 |
This model is based on the [RoBERTa base model](https://huggingface.co/roberta-base) (125 M parameters)
|
22 |
-
fine-tuned for 20 epochs on a poetry dataset of 51 MB,
|
|
|
23 |
|
24 |
The model replaces a masked word, indicated by the `<mask>` tag, with a word associated with **happiness**, while preserving fluency.
|
25 |
Caution: the emotion (here, **happiness**) only biases the choice of words with respect to the base model, but do not expect to find
|
|
|
19 |
# roberta-poetry-happiness-crpo
|
20 |
|
21 |
This model is based on the [RoBERTa base model](https://huggingface.co/roberta-base) (125 M parameters)
|
22 |
+
fine-tuned for 20 epochs on a poetry dataset of 51 MB (373k lines, 7.8M words). This dataset was extracted from
|
23 |
+
the [Gutenberg Poetry Corpus](https://github.com/aparrish/gutenberg-poetry-corpus) using an automatic classifier for **happiness**.
|
24 |
|
25 |
The model replaces a masked word, indicated by the `<mask>` tag, with a word associated with **happiness**, while preserving fluency.
|
26 |
Caution: the emotion (here, **happiness**) only biases the choice of words with respect to the base model, but do not expect to find
|