Update README.md
Browse files
README.md
CHANGED
@@ -38,8 +38,8 @@ You can use this model directly with a pipeline for masked language modeling:
|
|
38 |
|
39 |
```python
|
40 |
>>> from transformers import pipeline
|
41 |
-
>>> unmasker = pipeline('fill-mask', model='nairaxo/
|
42 |
-
>>> unmasker("rais wa [MASK] ya tanzania
|
43 |
|
44 |
|
45 |
```
|
@@ -48,9 +48,9 @@ Here is how to use this model to get the features of a given text in PyTorch:
|
|
48 |
|
49 |
```python
|
50 |
from transformers import BertTokenizer, BertModel
|
51 |
-
tokenizer = BertTokenizer.from_pretrained('nairaxo/
|
52 |
-
model = BertModel.from_pretrained("nairaxo/
|
53 |
-
text = "
|
54 |
encoded_input = tokenizer(text, return_tensors='pt')
|
55 |
output = model(**encoded_input)
|
56 |
```
|
@@ -59,9 +59,9 @@ and in TensorFlow:
|
|
59 |
|
60 |
```python
|
61 |
from transformers import BertTokenizer, TFBertModel
|
62 |
-
tokenizer = BertTokenizer.from_pretrained('nairaxo/
|
63 |
-
model = TFBertModel.from_pretrained("nairaxo/
|
64 |
-
text = "
|
65 |
encoded_input = tokenizer(text, return_tensors='tf')
|
66 |
output = model(encoded_input)
|
67 |
```
|
|
|
38 |
|
39 |
```python
|
40 |
>>> from transformers import pipeline
|
41 |
+
>>> unmasker = pipeline('fill-mask', model='nairaxo/bantulm')
|
42 |
+
>>> unmasker("rais wa [MASK] ya tanzania")
|
43 |
|
44 |
|
45 |
```
|
|
|
48 |
|
49 |
```python
|
50 |
from transformers import BertTokenizer, BertModel
|
51 |
+
tokenizer = BertTokenizer.from_pretrained('nairaxo/bantulm')
|
52 |
+
model = BertModel.from_pretrained("nairaxo/bantulm")
|
53 |
+
text = "rais wa jamhuri ya tanzania"
|
54 |
encoded_input = tokenizer(text, return_tensors='pt')
|
55 |
output = model(**encoded_input)
|
56 |
```
|
|
|
59 |
|
60 |
```python
|
61 |
from transformers import BertTokenizer, TFBertModel
|
62 |
+
tokenizer = BertTokenizer.from_pretrained('nairaxo/bantulm')
|
63 |
+
model = TFBertModel.from_pretrained("nairaxo/bantulm")
|
64 |
+
text = "rais wa jamhuri ya tanzania"
|
65 |
encoded_input = tokenizer(text, return_tensors='tf')
|
66 |
output = model(encoded_input)
|
67 |
```
|