stefanbschneider
commited on
Commit
•
8f2d608
1
Parent(s):
38c4b10
Add model card
Browse files
README.md
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- glue
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
metrics:
|
8 |
+
- f1
|
9 |
+
- accuracy
|
10 |
+
tags:
|
11 |
+
- dummy
|
12 |
+
- language
|
13 |
+
- paraphrasing
|
14 |
+
---
|
15 |
+
|
16 |
+
# Dummy Model based on BERT (uncased)
|
17 |
+
|
18 |
+
This is a fine-tuned version of [`bert-base-uncased`](https://huggingface.co/bert-base-uncased) for detecting whether two sentences are paraphrases.
|
19 |
+
Following the [HuggingFace course](https://huggingface.co/learn/nlp-course/chapter3/3?fw=pt).
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
Pretty much the same as the original BERT: https://huggingface.co/bert-base-uncased
|
24 |
+
With a new head, fine-tuned for paraphrasing.
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
Intended use: None. This is just a test :)
|
29 |
+
Limitations: Idk
|
30 |
+
|
31 |
+
## How to use
|
32 |
+
|
33 |
+
```python
|
34 |
+
from transformers import pipeline
|
35 |
+
|
36 |
+
pipe = pipeline("text-classification", model="stefanbschneider/bert-base-uncased-dummy")
|
37 |
+
sentence1 = 'Amrozi accused his brother , whom he called " the witness " , of deliberately distorting his evidence .'
|
38 |
+
sentence2 = 'Referring to him as only " the witness " , Amrozi accused his brother of deliberately distorting his evidence .'
|
39 |
+
pipe([sentence1, sentence2])
|