Update README.md
Browse files
README.md
CHANGED
@@ -4,12 +4,10 @@ language:
|
|
4 |
- en
|
5 |
pipeline_tag: text2text-generation
|
6 |
---
|
7 |
-
#
|
8 |
|
9 |
## Model Details
|
10 |
|
11 |
-
### Model Description
|
12 |
-
|
13 |
- **Model type:** Text-to-Text Generation
|
14 |
- **Language(s) (NLP):** English
|
15 |
- **License:** MIT License
|
@@ -26,22 +24,14 @@ from transformers import pipeline
|
|
26 |
|
27 |
pipe = pipeline("text2text-generation", model="textgain/News2Topic-T5-base")
|
28 |
|
29 |
-
```
|
30 |
-
# Example usage
|
31 |
-
|
32 |
-
```
|
33 |
news_text = "Your news text here."
|
34 |
print(pipe(news_text))
|
35 |
```
|
36 |
|
37 |
## Training Details
|
38 |
|
39 |
-
### Training Data
|
40 |
-
|
41 |
The News2Topic T5-base model was trained on a 21K sample of the "newsroom" dataset annotated with synthetic data generated by GPT-3.5-turbo
|
42 |
|
43 |
-
### Training Procedure
|
44 |
-
|
45 |
The model was trained for 3 epochs, with a learning rate of 0.00001, a maximum sequence length of 512, and a training batch size of 12.
|
46 |
|
47 |
## Citation
|
|
|
4 |
- en
|
5 |
pipeline_tag: text2text-generation
|
6 |
---
|
7 |
+
# News2Topic-T5-base
|
8 |
|
9 |
## Model Details
|
10 |
|
|
|
|
|
11 |
- **Model type:** Text-to-Text Generation
|
12 |
- **Language(s) (NLP):** English
|
13 |
- **License:** MIT License
|
|
|
24 |
|
25 |
pipe = pipeline("text2text-generation", model="textgain/News2Topic-T5-base")
|
26 |
|
|
|
|
|
|
|
|
|
27 |
news_text = "Your news text here."
|
28 |
print(pipe(news_text))
|
29 |
```
|
30 |
|
31 |
## Training Details
|
32 |
|
|
|
|
|
33 |
The News2Topic T5-base model was trained on a 21K sample of the "newsroom" dataset annotated with synthetic data generated by GPT-3.5-turbo
|
34 |
|
|
|
|
|
35 |
The model was trained for 3 epochs, with a learning rate of 0.00001, a maximum sequence length of 512, and a training batch size of 12.
|
36 |
|
37 |
## Citation
|