Summarization
Transformers
PyTorch
Safetensors
Portuguese
t5
text2text-generation
pt-br
abstractive summarization
text-generation-inference
Instructions to use recogna-nlp/ptt5-base-summ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use recogna-nlp/ptt5-base-summ with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("summarization", model="recogna-nlp/ptt5-base-summ")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("recogna-nlp/ptt5-base-summ") model = AutoModelForSeq2SeqLM.from_pretrained("recogna-nlp/ptt5-base-summ", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -125,7 +125,7 @@ from transformers import T5Tokenizer
|
|
| 125 |
from transformers import T5Model, T5ForConditionalGeneration
|
| 126 |
|
| 127 |
token_name = 'unicamp-dl/ptt5-base-portuguese-vocab'
|
| 128 |
-
model_name = '
|
| 129 |
|
| 130 |
tokenizer = T5Tokenizer.from_pretrained(token_name )
|
| 131 |
model_pt = T5ForConditionalGeneration.from_pretrained(model_name)
|
|
|
|
| 125 |
from transformers import T5Model, T5ForConditionalGeneration
|
| 126 |
|
| 127 |
token_name = 'unicamp-dl/ptt5-base-portuguese-vocab'
|
| 128 |
+
model_name = 'recogna-nlp/ptt5-base-summ'
|
| 129 |
|
| 130 |
tokenizer = T5Tokenizer.from_pretrained(token_name )
|
| 131 |
model_pt = T5ForConditionalGeneration.from_pretrained(model_name)
|