Update README.md
Browse files
README.md
CHANGED
@@ -41,6 +41,7 @@ Which will output:
|
|
41 |
[{'generated_text': 'who _ _ researched something _ _ ?<extra_id_7> Luke',
|
42 |
'QAs': [{'question': 'who researched something ?', 'answers': ['Luke']}]}]
|
43 |
```
|
|
|
44 |
|
45 |
Notice that you need to specify which word in the sentence is the predicate, about which the question will interrogate. By default, you should precede the predicate with the `<predicate>` symbol, but you can also specify your own predicate marker:
|
46 |
```python
|
@@ -50,5 +51,6 @@ In addition, you can specify additional kwargs for controling the model's decodi
|
|
50 |
```python
|
51 |
pipe("The student was interested in Luke 's <predicate> research about see animals .", verb_form="research", predicate_type="nominal", num_beams=3)
|
52 |
```
|
53 |
-
|
|
|
54 |
|
|
|
41 |
[{'generated_text': 'who _ _ researched something _ _ ?<extra_id_7> Luke',
|
42 |
'QAs': [{'question': 'who researched something ?', 'answers': ['Luke']}]}]
|
43 |
```
|
44 |
+
You can learn more about using `transformers.pipelines` in the [official docs](https://huggingface.co/docs/transformers/main_classes/pipelines).
|
45 |
|
46 |
Notice that you need to specify which word in the sentence is the predicate, about which the question will interrogate. By default, you should precede the predicate with the `<predicate>` symbol, but you can also specify your own predicate marker:
|
47 |
```python
|
|
|
51 |
```python
|
52 |
pipe("The student was interested in Luke 's <predicate> research about see animals .", verb_form="research", predicate_type="nominal", num_beams=3)
|
53 |
```
|
54 |
+
|
55 |
+
|
56 |
|