Commit
•
b986aeb
1
Parent(s):
4d6a5e2
Update README.md
Browse files
README.md
CHANGED
|
@@ -8,7 +8,7 @@ widget:
|
|
| 8 |
|
| 9 |
## Overview
|
| 10 |
|
| 11 |
-
**Model Description:** roberta-large-faithcritic is the [RoBERTa large model](https://huggingface.co/roberta-large) fine-tuned on the [FaithDial](https://huggingface.co/datasets/McGill-NLP/FaithDial) dataset. The objective is to predict whether an utterance is faithful or not, given the source knowledge.
|
| 12 |
|
| 13 |
The hyperparameters are provided in [hparams.yml](https://huggingface.co/McGill-NLP/roberta-large-faithcritic/blob/main/hparams.yaml). To know more about how to train a critic model, visit [our repo](https://github.com/McGill-NLP/FaithDial).
|
| 14 |
|
|
|
|
| 8 |
|
| 9 |
## Overview
|
| 10 |
|
| 11 |
+
**Model Description:** roberta-large-faithcritic is the [RoBERTa large model](https://huggingface.co/roberta-large) fine-tuned on the FaithCritic, a derivative of the [FaithDial](https://huggingface.co/datasets/McGill-NLP/FaithDial) dataset. The objective is to predict whether an utterance is faithful or not, given the source knowledge.
|
| 12 |
|
| 13 |
The hyperparameters are provided in [hparams.yml](https://huggingface.co/McGill-NLP/roberta-large-faithcritic/blob/main/hparams.yaml). To know more about how to train a critic model, visit [our repo](https://github.com/McGill-NLP/FaithDial).
|
| 14 |
|