Commit
•
41ca872
1
Parent(s):
0be3b8b
Update README.md
Browse files
README.md
CHANGED
|
@@ -32,6 +32,15 @@ This model is based on [microsoft/deberta-v3-base](https://huggingface.co/micros
|
|
| 32 |
* [SummaC Benchmark](https://aclanthology.org/2022.tacl-1.10.pdf) (Test Split) - 0.764 Balanced Accuracy, 0.831 AUC Score
|
| 33 |
* [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
|
| 34 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
## Usage with Sentencer Transformers (Recommended)
|
| 36 |
|
| 37 |
The model can be used like this, on pairs of documents, passed as a list of list of strings (```List[List[str]]]```):
|
|
|
|
| 32 |
* [SummaC Benchmark](https://aclanthology.org/2022.tacl-1.10.pdf) (Test Split) - 0.764 Balanced Accuracy, 0.831 AUC Score
|
| 33 |
* [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
|
| 34 |
|
| 35 |
+
## Note about using the Inference API Widget on the Right
|
| 36 |
+
To use the model with the widget, you need to pass both documents as a single string separated with [SEP]. For example:
|
| 37 |
+
|
| 38 |
+
* A man walks into a bar and buys a drink [SEP] A bloke swigs alcohol at a pub
|
| 39 |
+
* A person on a horse jumps over a broken down airplane. [SEP] A person is at a diner, ordering an omelette.
|
| 40 |
+
* A person on a horse jumps over a broken down airplane. [SEP] A person is outdoors, on a horse.
|
| 41 |
+
|
| 42 |
+
etc. See examples below for expected probability scores.
|
| 43 |
+
|
| 44 |
## Usage with Sentencer Transformers (Recommended)
|
| 45 |
|
| 46 |
The model can be used like this, on pairs of documents, passed as a list of list of strings (```List[List[str]]]```):
|