T5-Base-Sum
This model is a fine-tuned version of T5
for summarization tasks. It was finetuned on 25000 training samples from the CNN Dailymail trainset, and is hosted on Hugging Face for easy access and use.
This model aspires to deliver precision, factual consistency, and conciseness, driven by a custom cyclic attention mechanism.
Model Usage
Below is an example of how to load and use this model for summarization:
from transformers import T5ForConditionalGeneration, T5Tokenizer
# Load the model and tokenizer from Hugging Face
model = T5ForConditionalGeneration.from_pretrained("Vijayendra/T5-Base-Sum")
tokenizer = T5Tokenizer.from_pretrained("Vijayendra/T5-Base-Sum")
# Example of using the model for summarization
article = """
Videos that say approved vaccines are dangerous and cause autism, cancer or infertility are among those that will be taken down, the company
said. The policy includes the termination of accounts of anti-vaccine influencers. Tech giants have been criticised for not doing more to
counter false health information on their sites. In July, US PresidentJoe Biden said social media platforms were largely responsible for
people's scepticism in getting vaccinated by spreading misinformation, and appealed for them to address the issue. YouTube, which is owned
by Google, said 130,000 videos were removed from its platform since last year, when it implemented a ban on content spreading misinformation
about Covid vaccines. In a blog post, the company said it had seen false claims about Covid jabs "spill over into misinformation about
vaccines in general". The new policy covers long-approved vaccines, such as those against measles or hepatitis B."We're expanding our medical
misinformation policies on YouTube with new guidelines on currently administered vaccines that are approved and confirmed to be safe and
effective by local health authorities and the WHO," the post said, referring to the World Health Organization.
"""
inputs = tokenizer.encode("summarize: " + article, return_tensors="pt", max_length=512, truncation=True)
summary_ids = model.generate(inputs, max_length=150, min_length=100, length_penalty=2.0, num_beams=4, early_stopping=True)
# Decode and print the summary
summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
print("Summary:")
print(summary)
# Example of a random article (can replace this with any article)
random_article = """
Artificial intelligence (AI) is intelligence demonstrated by machines, as opposed to the natural intelligence displayed by animals including humans.
Leading AI textbooks define the field as the study of "intelligent agents": any system that perceives its environment and takes actions that maximize its chance of achieving its goals.
Some popular accounts use the term "artificial intelligence" to describe machines that mimic "cognitive" functions that humans associate with the human mind, such as "learning" and "problem-solving".
As machines become increasingly capable, tasks considered to require "intelligence" are often removed from the definition of AI, a phenomenon known as the AI effect.
A quip in Tesler's Theorem says "AI is whatever hasn't been done yet.
"""
# Tokenize the input article
inputs = tokenizer.encode("summarize: " + random_article, return_tensors="pt", max_length=512, truncation=True)
# Generate summary
summary_ids = model.generate(inputs, max_length=150, min_length=100, length_penalty=3.0, num_beams=7, early_stopping=False)
# Decode and print the summary
summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
print("Summary:")
print(summary)
#Compare with some other models
from transformers import T5ForConditionalGeneration, T5Tokenizer, PegasusTokenizer, PegasusForConditionalGeneration, BartForConditionalGeneration, BartTokenizer
# Function to summarize with any model
def summarize_article(article, model, tokenizer):
inputs = tokenizer.encode("summarize: " + article, return_tensors="pt", max_length=512, truncation=True)
summary_ids = model.generate(inputs, max_length=150, min_length=100, length_penalty=2.0, num_beams=4, early_stopping=True)
summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
return summary
# Load our fine-tuned T5 model and tokenizer
t5_model_custom = T5ForConditionalGeneration.from_pretrained("Vijayendra/T5-Base-Sum")
t5_tokenizer_custom = T5Tokenizer.from_pretrained("Vijayendra/T5-Base-Sum")
# Load a different pretrained T5 model for summarization (e.g., "t5-small" fine-tuned on CNN/DailyMail)
t5_model_pretrained = T5ForConditionalGeneration.from_pretrained("csebuetnlp/mT5_multilingual_XLSum")
t5_tokenizer_pretrained = T5Tokenizer.from_pretrained("csebuetnlp/mT5_multilingual_XLSum")
# Load Pegasus model and tokenizer
pegasus_model = PegasusForConditionalGeneration.from_pretrained("google/pegasus-xsum")
pegasus_tokenizer = PegasusTokenizer.from_pretrained("google/pegasus-xsum")
# Load BART model and tokenizer
bart_model = BartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn")
bart_tokenizer = BartTokenizer.from_pretrained("facebook/bart-large-cnn")
# Example article for summarization
article = """
Videos that say approved vaccines are dangerous and cause autism, cancer or infertility are among those that will be taken down, the company
said. The policy includes the termination of accounts of anti-vaccine influencers. Tech giants have been criticised for not doing more to
counter false health information on their sites. In July, US PresidentJoe Biden said social media platforms were largely responsible for
people's scepticism in getting vaccinated by spreading misinformation, and appealed for them to address the issue. YouTube, which is owned
by Google, said 130,000 videos were removed from its platform since last year, when it implemented a ban on content spreading misinformation
about Covid vaccines. In a blog post, the company said it had seen false claims about Covid jabs "spill over into misinformation about
vaccines in general". The new policy covers long-approved vaccines, such as those against measles or hepatitis B."We're expanding our medical
misinformation policies on YouTube with new guidelines on currently administered vaccines that are approved and confirmed to be safe and
effective by local health authorities and the WHO," the post said, referring to the World Health Organization.
"""
# Summarize with our fine-tuned T5 model
t5_summary_custom = summarize_article(article, t5_model_custom, t5_tokenizer_custom)
# Summarize with the pretrained T5 model for summarization
t5_summary_pretrained = summarize_article(article, t5_model_pretrained, t5_tokenizer_pretrained)
# Summarize with Pegasus model
pegasus_summary = summarize_article(article, pegasus_model, pegasus_tokenizer)
# Summarize with BART model
bart_summary = summarize_article(article, bart_model, bart_tokenizer)
# Print summaries for comparison
print("T5 base with Cyclic Attention Summary:")
print(t5_summary_custom)
print("\nPretrained mT5_multilingual_XLSum Summary:")
print(t5_summary_pretrained)
print("\nPegasus Xsum Summary:")
print(pegasus_summary)
print("\nBART Large CNN Summary:")
print(bart_summary)
- Downloads last month
- 10
Model tree for Vijayendra/T5-Base-Sum
Base model
google-t5/t5-base