Ihor's picture
Create README.md
96b4cbc verified
metadata
license: apache-2.0
language:
  - en
pipeline_tag: text2text-generation

flan-t5-small-for-classification

This is an additional fine-tuned flan-t5-large model on many classification datasets.

The model supports prompt-tuned classification and is suitable for complex classification settings such as resumes classification by criteria.

You can use the model simply generating the text class name or using our unlimited-classifier.

The library allows to set constraints on generation and classify text into millions of classes.

How to use:

To use it with transformers library take a look into the following code snippet:

# pip install accelerate
from transformers import T5Tokenizer, T5ForConditionalGeneration

tokenizer = T5Tokenizer.from_pretrained("knowledgator/flan-t5-large-for-classification")
model = T5ForConditionalGeneration.from_pretrained("knowledgator/flan-t5-large-for-classification", device_map="auto")

input_text = "Define sentiment of the following text: I love to travel and someday I will see the world."
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")

outputs = model.generate(input_ids)
print(tokenizer.decode(outputs[0]))

Using unlimited-classifier

# pip install unlimited-classifier

from unlimited_classifier import TextClassifier

classifier = TextClassifier(
    labels=[
        'positive',
        'negative',
        'neutral'    
    ],
    model='knowledgator/flan-t5-large-for-classification',
    tokenizer='knowledgator/flan-t5-large-for-classification',
)
output = classifier.invoke(input_text)
print(output)