Update READM.md
Browse files
README.md
CHANGED
@@ -1,23 +1,16 @@
|
|
1 |
-
---
|
2 |
-
language: "en"
|
3 |
-
tags:
|
4 |
-
- paraphrase-generation
|
5 |
-
- text-generation
|
6 |
-
|
7 |
-
---
|
8 |
# Simple model for Paraphrase Generation
|
9 |
β
|
10 |
## Model description
|
11 |
β
|
12 |
-
T5-based
|
13 |
β
|
14 |
## How to use
|
15 |
β
|
16 |
```python
|
17 |
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
|
18 |
-
|
19 |
-
tokenizer = AutoTokenizer.from_pretrained("
|
20 |
-
model = AutoModelForSeq2SeqLM.from_pretrained("
|
21 |
β
|
22 |
sentence = "This is something which i cannot understand at all"
|
23 |
text = "paraphrase: " + sentence + " </s>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
# Simple model for Paraphrase Generation
|
2 |
β
|
3 |
## Model description
|
4 |
β
|
5 |
+
T5-based model for generating paraphrased sentences. It is trained on the labeled [MSRP](https://www.microsoft.com/en-us/download/details.aspx?id=52398) and [Google PAWS](https://github.com/google-research-datasets/paws) dataset.
|
6 |
β
|
7 |
## How to use
|
8 |
β
|
9 |
```python
|
10 |
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
|
11 |
+
|
12 |
+
tokenizer = AutoTokenizer.from_pretrained("shrishail/t5_paraphrase_msrp_paws")
|
13 |
+
model = AutoModelForSeq2SeqLM.from_pretrained("shrishail/t5_paraphrase_msrp_paws")
|
14 |
β
|
15 |
sentence = "This is something which i cannot understand at all"
|
16 |
text = "paraphrase: " + sentence + " </s>"
|