Commit ·
250806e
1
Parent(s): 040675b
Update README.md
Browse files
README.md
CHANGED
|
@@ -28,7 +28,7 @@ This model is based on [microsoft/deberta-v3-base](https://huggingface.co/micros
|
|
| 28 |
* [SummaC Benchmark](https://aclanthology.org/2022.tacl-1.10.pdf) (Test Split) - 0.764 Balanced Accuracy, 0.831 AUC Score
|
| 29 |
* [AnyScale Ranking Test for Hallucinations](https://www.anyscale.com/blog/llama-2-is-about-as-factually-accurate-as-gpt-4-for-summaries-and-is-30x-cheaper) - 86.6 % Accuracy
|
| 30 |
|
| 31 |
-
## Usage
|
| 32 |
|
| 33 |
The model can be used like this:
|
| 34 |
|
|
@@ -53,7 +53,7 @@ array([0.61051559, 0.00047493709, 0.99639291, 0.00021221573, 0.99599433, 0.00141
|
|
| 53 |
```
|
| 54 |
|
| 55 |
## Usage with Transformers AutoModel
|
| 56 |
-
You can use the model also directly with Transformers library (without SentenceTransformers library):
|
| 57 |
|
| 58 |
```python
|
| 59 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
|
|
|
| 28 |
* [SummaC Benchmark](https://aclanthology.org/2022.tacl-1.10.pdf) (Test Split) - 0.764 Balanced Accuracy, 0.831 AUC Score
|
| 29 |
* [AnyScale Ranking Test for Hallucinations](https://www.anyscale.com/blog/llama-2-is-about-as-factually-accurate-as-gpt-4-for-summaries-and-is-30x-cheaper) - 86.6 % Accuracy
|
| 30 |
|
| 31 |
+
## Usage with Sentencer Transformers (Recommended)
|
| 32 |
|
| 33 |
The model can be used like this:
|
| 34 |
|
|
|
|
| 53 |
```
|
| 54 |
|
| 55 |
## Usage with Transformers AutoModel
|
| 56 |
+
You can use the model also directly with Transformers library (without the SentenceTransformers library):
|
| 57 |
|
| 58 |
```python
|
| 59 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|