Instructions to use jla25/squareV3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jla25/squareV3 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("jla25/squareV3") model = AutoModelForSeq2SeqLM.from_pretrained("jla25/squareV3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update handler.py
Browse files- handler.py +1 -1
handler.py
CHANGED
|
@@ -22,7 +22,7 @@ class EndpointHandler:
|
|
| 22 |
# Prompt personalizado para guiar al modelo
|
| 23 |
input_text = f"Generate a valid JSON capturing data from this text:{data['inputs']}"
|
| 24 |
print(f"Prompt generado para el modelo: {input_text}")
|
| 25 |
-
|
| 26 |
tokens = self.tokenizer(input_text, return_tensors="pt", truncation=True, padding="max_length", max_length=1024)
|
| 27 |
return tokens
|
| 28 |
|
|
|
|
| 22 |
# Prompt personalizado para guiar al modelo
|
| 23 |
input_text = f"Generate a valid JSON capturing data from this text:{data['inputs']}"
|
| 24 |
print(f"Prompt generado para el modelo: {input_text}")
|
| 25 |
+
input_text = input_text.encode("utf-8").decode("utf-8")
|
| 26 |
tokens = self.tokenizer(input_text, return_tensors="pt", truncation=True, padding="max_length", max_length=1024)
|
| 27 |
return tokens
|
| 28 |
|