Summarization
Transformers
PyTorch
Core ML
ONNX
Safetensors
English
t5
text2text-generation
text-generation-inference
Instructions to use Falconsai/text_summarization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Falconsai/text_summarization 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="Falconsai/text_summarization")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Falconsai/text_summarization") model = AutoModelForSeq2SeqLM.from_pretrained("Falconsai/text_summarization") - Inference
- Notebooks
- Google Colab
- Kaggle
Max Model Input Length
#11
by sushant-nair - opened
Hello dear @maintainers,
Can you please tell what is the maximum number of tokens that the model can accept at a time? I am having difficulty finding documentation that reveals this.
Thanks
1024 if I remember correctly. It is based on the T5small model
mstatt changed discussion status to closed
Actually, I found out later...
It is 512