Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
This model is a fine-tuned version of deepset/xlm-roberta-large-squad2 on the milqa dataset.
|
2 |
+
|
3 |
+
Packages to install for large roberta model:
|
4 |
+
```py
|
5 |
+
sentencepiece==0.1.97
|
6 |
+
protobuf==3.20.0
|
7 |
+
```
|
8 |
+
|
9 |
+
How to use:
|
10 |
+
```py
|
11 |
+
from transformers import pipeline
|
12 |
+
qa_pipeline = pipeline(
|
13 |
+
"question-answering",
|
14 |
+
model = "ZTamas/xlm-roberta-large-squad2-qa-milqa-impossible",
|
15 |
+
tokenizer = "ZTamas/xlm-roberta-large-squad2-qa-milqa-impossible",
|
16 |
+
device = 0, #GPU selection, -1 on CPU
|
17 |
+
handle_impossible_answer = True,
|
18 |
+
max_answer_len = 50 #This can be modified
|
19 |
+
)
|
20 |
+
|
21 |
+
predictions = qa_pipeline({
|
22 |
+
'context': context,
|
23 |
+
'question': question
|
24 |
+
})
|
25 |
+
|
26 |
+
print(predictions)
|
27 |
+
|
28 |
+
```
|