Instructions to use logicreasoning/LogiT5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use logicreasoning/LogiT5 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("logicreasoning/LogiT5") model = AutoModelForSeq2SeqLM.from_pretrained("logicreasoning/LogiT5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,12 +2,3 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
|
| 5 |
-
model_name = 'logicreasoning/LogiT5'
|
| 6 |
-
tokenize = AutoTokenizer.from_pretrained(model_name)
|
| 7 |
-
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
|
| 8 |
-
device = 'cuda:0' if torch.cuda.is_available() else 'cpu'
|
| 9 |
-
input_text = '' #your input text here
|
| 10 |
-
input = tokenize(input, return_tensors='pt', padding=True).to(device)
|
| 11 |
-
model = model.to(device)
|
| 12 |
-
output = model.generate(*input, max_length=1024)
|
| 13 |
-
prediction = tokenize.decode(output[0],skip_special_tokens=True)
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|