updated model name
Browse files- .vscode/settings.json +7 -0
- README.md +3 -3
.vscode/settings.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"workbench.colorCustomizations": {
|
3 |
+
"activityBar.background": "#0F3332",
|
4 |
+
"titleBar.activeBackground": "#144746",
|
5 |
+
"titleBar.activeForeground": "#F5FCFC"
|
6 |
+
}
|
7 |
+
}
|
README.md
CHANGED
@@ -12,15 +12,15 @@ Bolbol-zaban/gpt2-persian is gpt2 language model that is trained with hyper para
|
|
12 |
3. The training dataset only include Persian text. All non-persian characters are replaced with especial tokens (e.g [LAT], [URL], [NUM])
|
13 |
|
14 |
Please refer to this [blog post](https://medium.com/@khashei/a-not-so-dangerous-ai-in-the-persian-language-39172a641c84) for further detail.
|
15 |
-
Also try the model [here](https://huggingface.co/
|
16 |
|
17 |
## How to use
|
18 |
You can use this model directly with a pipeline for text generation:
|
19 |
|
20 |
```python
|
21 |
from transformers import pipeline, AutoTokenizer, GPT2LMHeadModel
|
22 |
-
tokenizer = AutoTokenizer.from_pretrained('
|
23 |
-
model = GPT2LMHeadModel.from_pretrained('
|
24 |
generator = pipeline('text-generation', model, tokenizer=tokenizer, config={'max_length':256})
|
25 |
sample = generator('در یک اتفاق شگفت انگیز، پژوهشگران')
|
26 |
```
|
|
|
12 |
3. The training dataset only include Persian text. All non-persian characters are replaced with especial tokens (e.g [LAT], [URL], [NUM])
|
13 |
|
14 |
Please refer to this [blog post](https://medium.com/@khashei/a-not-so-dangerous-ai-in-the-persian-language-39172a641c84) for further detail.
|
15 |
+
Also try the model [here](https://huggingface.co/bolbolzaban/gpt2-persian?text=%D8%AF%D8%B1+%DB%8C%DA%A9+%D8%A7%D8%AA%D9%81%D8%A7%D9%82+%D8%B4%DA%AF%D9%81%D8%AA+%D8%A7%D9%86%DA%AF%DB%8C%D8%B2%D8%8C+%D9%BE%DA%98%D9%88%D9%87%D8%B4%DA%AF%D8%B1%D8%A7%D9%86) or on [Bolbolzaban.com](http://www.bolbolzaban.com/text).
|
16 |
|
17 |
## How to use
|
18 |
You can use this model directly with a pipeline for text generation:
|
19 |
|
20 |
```python
|
21 |
from transformers import pipeline, AutoTokenizer, GPT2LMHeadModel
|
22 |
+
tokenizer = AutoTokenizer.from_pretrained('bolbolzaban/gpt2-persian')
|
23 |
+
model = GPT2LMHeadModel.from_pretrained('bolbolzaban/gpt2-persian')
|
24 |
generator = pipeline('text-generation', model, tokenizer=tokenizer, config={'max_length':256})
|
25 |
sample = generator('در یک اتفاق شگفت انگیز، پژوهشگران')
|
26 |
```
|