Downloads · 30 days
11
2% of all-time downloads
flan-t5-base-xsum
tripplyons/flan-t5-base-xsum
flan-t5-base-xsum is a machine learning model from tripplyons. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
Use the original flan-t5-base tokenizer:
All-time downloads
635
Public
Repo size
8.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin998 MB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Dec 5, 2022
- Updated
- Dec 9, 2022
- SHA
- c62cf6ad
Model card
From the Hugging Face model README
google/flan-t5-base finetuned on xsum using LoRA with adapter-transformers
Usage
Use the original flan-t5-base tokenizer:
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-base")
model = AutoModelForSeq2SeqLM.from_pretrained("tripplyons/flan-t5-base-xsum")
input_text = "summarize: The ex-Reading defender denied fraudulent trading charges relating to the Sodje Sports Foundation - a charity to raise money for Nigerian sport. Mr Sodje, 37, is jointly charged with elder brothers Efe, 44, Bright, 50 and Stephen, 42. Appearing at the Old Bailey earlier, all four denied the offence. The charge relates to offences which allegedly took place between 2008 and 2014. Sam, from Kent, Efe and Bright, of Greater Manchester, and Stephen, from Bexley, are due to stand trial in July. They were all released on bail."
input_ids = tokenizer([input_text], max_length=512, truncation=True, padding=True, return_tensors='pt')['input_ids']
output = model.generate(input_ids, max_length=512)
output_text = tokenizer.decode(output[0], skip_special_tokens=True)
print(output_text)
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- Dec 5, 2022
- Updated
- Dec 9, 2022