Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# keytotext
|
| 2 |
+
|
| 3 |
+
Idea is to build a model which will take keywords as inputs and generate sentences as outputs.
|
| 4 |
+
|
| 5 |
+
### Model:
|
| 6 |
+
|
| 7 |
+
Two Models have been built:
|
| 8 |
+
|
| 9 |
+
- Using T5-base size = 850 MB can be found here: https://huggingface.co/gagan3012/keytotext
|
| 10 |
+
- Using T5-small size = 230 MB can be found here: https://huggingface.co/gagan3012/keytotext-small
|
| 11 |
+
|
| 12 |
+
#### Usage:
|
| 13 |
+
|
| 14 |
+
```python
|
| 15 |
+
from transformers import AutoTokenizer, AutoModelWithLMHead
|
| 16 |
+
|
| 17 |
+
tokenizer = AutoTokenizer.from_pretrained("gagan3012/keytotext-small")
|
| 18 |
+
|
| 19 |
+
model = AutoModelWithLMHead.from_pretrained("gagan3012/keytotext-small")
|
| 20 |
+
```
|
| 21 |
+
|
| 22 |
+
### Demo:
|
| 23 |
+
|
| 24 |
+
[](https://share.streamlit.io/gagan3012/keytotext/app.py)
|
| 25 |
+
|
| 26 |
+
https://share.streamlit.io/gagan3012/keytotext/app.py
|
| 27 |
+
|
| 28 |
+

|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
### Example:
|
| 32 |
+
|
| 33 |
+
['India', 'Wedding'] -> We are celebrating today in New Delhi with three wedding anniversary parties.
|