Commit
•
bf7fd9f
1
Parent(s):
b56811f
Update README.md
Browse files
README.md
CHANGED
|
@@ -27,7 +27,7 @@ co2_eq_emissions:
|
|
| 27 |
---
|
| 28 |
# RewardModel (Portuguese)
|
| 29 |
|
| 30 |
-
The
|
| 31 |
|
| 32 |
The model was trained with a dataset composed of `prompt`, `prefered_completions`, and `rejected_completions`.
|
| 33 |
## Details
|
|
@@ -47,7 +47,7 @@ This repository has the [source code](https://github.com/Nkluge-correa/Aira) use
|
|
| 47 |
|
| 48 |
## Usage
|
| 49 |
|
| 50 |
-
Here's an example of how to use the
|
| 51 |
|
| 52 |
```python
|
| 53 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
|
@@ -139,4 +139,4 @@ IA e reclamam do que as máquinas fazem. Score: -10.744
|
|
| 139 |
|
| 140 |
## License
|
| 141 |
|
| 142 |
-
|
|
|
|
| 27 |
---
|
| 28 |
# RewardModel (Portuguese)
|
| 29 |
|
| 30 |
+
The RewardModelPT is a [BERT](https://huggingface.co/neuralmind/bert-base-portuguese-cased) model that can be used to score the quality of a completion for a given prompt.
|
| 31 |
|
| 32 |
The model was trained with a dataset composed of `prompt`, `prefered_completions`, and `rejected_completions`.
|
| 33 |
## Details
|
|
|
|
| 47 |
|
| 48 |
## Usage
|
| 49 |
|
| 50 |
+
Here's an example of how to use the RewardModelPT to score the quality of a response to a given prompt:
|
| 51 |
|
| 52 |
```python
|
| 53 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
|
|
|
| 139 |
|
| 140 |
## License
|
| 141 |
|
| 142 |
+
RewardModelPT is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
|