Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,52 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
+
## Introduction
|
| 5 |
+
A paraphrase generation model that *attempts* to give you some control over the output text using natural language. You can do this by prepending the following to the input text:
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
```
|
| 9 |
+
Paraphrase: {distance_keyword} changes, {word_length_keyword} input.
|
| 10 |
+
```
|
| 11 |
+
|
| 12 |
+
### distance_keyword
|
| 13 |
+
This tells the model how much to change the input text. There are four options:
|
| 14 |
+
1. small
|
| 15 |
+
2. medium
|
| 16 |
+
3. large
|
| 17 |
+
4. gigantic
|
| 18 |
+
|
| 19 |
+
### word_length_keyword:
|
| 20 |
+
Tells the model how long to make the output text relative to the input. There are three options:
|
| 21 |
+
1. reduce
|
| 22 |
+
2. match
|
| 23 |
+
3. expand
|
| 24 |
+
|
| 25 |
+
If you only want to paraphrase and don't necessarily care about the specifics of the output, you can also prepend "Paraphrase: " alone or skip the prepending all together and just input the text you wish to paraphrase.
|
| 26 |
+
|
| 27 |
+
## How to use:
|
| 28 |
+
|
| 29 |
+
Initializing model using GPU and Bfloat16 precision:
|
| 30 |
+
|
| 31 |
+
```python:
|
| 32 |
+
from transformers import pipeline
|
| 33 |
+
from torch import bfloat16
|
| 34 |
+
|
| 35 |
+
para_gen = pipeline('text2text-generation', model="imjeffhi/paraphrase_generator", tokenizer="imjeffhi/paraphrase_generator", device=0, torch_dtype=bfloat16)
|
| 36 |
+
```
|
| 37 |
+
|
| 38 |
+
Calling model:
|
| 39 |
+
|
| 40 |
+
```python:
|
| 41 |
+
options_phrase = "Paraphrase: large changes, match input."
|
| 42 |
+
input_text = "A paraphrase is a restatement of the meaning of a text or passage using other words."
|
| 43 |
+
output = para_gen(f"{options_phrase} {input_text}", do_sample=True, top_k=10, num_return_sequences=5)
|
| 44 |
+
```
|
| 45 |
+
Output:
|
| 46 |
+
```python:
|
| 47 |
+
[{'generated_text': 'A paraphrase is a modification of the meaning or expression of a text or passage by using other words.'},
|
| 48 |
+
{'generated_text': 'A paraphrase is a continuation of the meaning of a text or a passage using other words.'},
|
| 49 |
+
{'generated_text': 'A paraphrase is the restatement of the meaning of a text or other passage containing other words.'},
|
| 50 |
+
{'generated_text': 'The paraphrase is a repetition of the meanings of a text or passage using other words.'},
|
| 51 |
+
{'generated_text': 'A paraphrase is a continuation of a sentence or passage by using other words.'}]
|
| 52 |
+
```
|