YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
This model bases on T5-base model, finetuned using bbc-news-summary dataset Example of using:
from transformers import pipeline, T5ForConditionalGeneration, T5Tokenizer
import torch
model_name = "Andrew0488/t5-summarizer"
model = T5ForConditionalGeneration.from_pretrained(model_name).cuda()
tokenizer = T5Tokenizer.from_pretrained(model_name)
def t5_summary(text: str):
inputs = tokenizer.encode(
"summarize: " + text,
return_tensors='pt',
max_length=2000,
truncation=True,
padding='max_length'
).to(torch.device("cuda"))
# Generate the summary
summary_ids = model.generate(
inputs,
max_length=250,
num_beams=5
)
return tokenizer.decode(summary_ids[0], skip_special_tokens=True)
- Downloads last month
- 192
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.