Instructions to use nashtur/postbox_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nashtur/postbox_v1 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("nashtur/postbox_v1") model = AutoModelForSeq2SeqLM.from_pretrained("nashtur/postbox_v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,7 @@ tags:
|
|
| 12 |
```
|
| 13 |
import torch
|
| 14 |
from transformers import PegasusForConditionalGeneration, PegasusTokenizer
|
| 15 |
-
model_name = '
|
| 16 |
torch_device = 'cuda' if torch.cuda.is_available() else 'cpu'
|
| 17 |
tokenizer = PegasusTokenizer.from_pretrained(model_name)
|
| 18 |
model = PegasusForConditionalGeneration.from_pretrained(model_name).to(torch_device)
|
|
|
|
| 12 |
```
|
| 13 |
import torch
|
| 14 |
from transformers import PegasusForConditionalGeneration, PegasusTokenizer
|
| 15 |
+
model_name = 'nashtur/postbox'
|
| 16 |
torch_device = 'cuda' if torch.cuda.is_available() else 'cpu'
|
| 17 |
tokenizer = PegasusTokenizer.from_pretrained(model_name)
|
| 18 |
model = PegasusForConditionalGeneration.from_pretrained(model_name).to(torch_device)
|