Update README.md
Browse files
README.md
CHANGED
|
@@ -24,7 +24,28 @@ You can use this model directly with a pipeline for masked language modeling:
|
|
| 24 |
>>> from transformers import pipeline
|
| 25 |
>>> unmasker = pipeline('fill-mask', model='uer/roberta-xlarge-wwm-chinese-cluecorpussmall')
|
| 26 |
>>> unmasker("北京是[MASK]国的首都。")
|
| 27 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
```
|
| 29 |
|
| 30 |
Here is how to use this model to get the features of a given text in PyTorch:
|
|
|
|
| 24 |
>>> from transformers import pipeline
|
| 25 |
>>> unmasker = pipeline('fill-mask', model='uer/roberta-xlarge-wwm-chinese-cluecorpussmall')
|
| 26 |
>>> unmasker("北京是[MASK]国的首都。")
|
| 27 |
+
[
|
| 28 |
+
{'score': 0.9298505783081055,
|
| 29 |
+
'token': 704,
|
| 30 |
+
'token_str': '中',
|
| 31 |
+
'sequence': '北 京 是 中 国 的 首 都 。'},
|
| 32 |
+
{'score': 0.05041525512933731,
|
| 33 |
+
'token': 2769,
|
| 34 |
+
'token_str': '我',
|
| 35 |
+
'sequence': '北 京 是 我 国 的 首 都 。'},
|
| 36 |
+
{'score': 0.004921116400510073,
|
| 37 |
+
'token': 4862,
|
| 38 |
+
'token_str': '祖',
|
| 39 |
+
'sequence': '北 京 是 祖 国 的 首 都 。'},
|
| 40 |
+
{'score': 0.0020684923510998487,
|
| 41 |
+
'token': 3696,
|
| 42 |
+
'token_str': '民',
|
| 43 |
+
'sequence': '北 京 是 民 国 的 首 都 。'},
|
| 44 |
+
{'score': 0.0018144999630749226,
|
| 45 |
+
'token': 3926,
|
| 46 |
+
'token_str': '清',
|
| 47 |
+
'sequence': '北 京 是 清 国 的 首 都 。'}
|
| 48 |
+
]
|
| 49 |
```
|
| 50 |
|
| 51 |
Here is how to use this model to get the features of a given text in PyTorch:
|