Moreno La Quatra
commited on
Commit
•
d880d9f
1
Parent(s):
94d162b
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 21 |
|
| 22 |
# distilgpt2-fables-demo
|
| 23 |
|
|
|
|
|
|
|
| 24 |
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on [demelin/understanding_fables](https://huggingface.co/datasets/demelin/understanding_fables) dataset.
|
| 25 |
It achieves the following results on the evaluation set:
|
| 26 |
- Loss: 3.2165
|
|
|
|
| 21 |
|
| 22 |
# distilgpt2-fables-demo
|
| 23 |
|
| 24 |
+
**Training:** The model has been trained using the script provided in the following repository https://github.com/MorenoLaQuatra/transformers-tasks-templates
|
| 25 |
+
|
| 26 |
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on [demelin/understanding_fables](https://huggingface.co/datasets/demelin/understanding_fables) dataset.
|
| 27 |
It achieves the following results on the evaluation set:
|
| 28 |
- Loss: 3.2165
|