Herb-Lab/LLM_housing_livability

🚀 Other links:

• 📝 Checkout our GitHub repository
• 🤗 Test the model with sentiment analysis on the Huggingface Space

Additional information about this model:

• The bart-large-mnli model page
• BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

The following instructions for model deployment is a slightly modified version from the The bart-large-mnli model page.

With the zero-shot classification pipeline

The model can be loaded with the zero-shot-classification pipeline like so:

from transformers.pipelines import pipeline
classifier = pipeline("zero-shot-classification",
                      model="Herb-Lab/LLM_housing_livability")

You can then use this pipeline to classify sequences into any of the class names you specify.

sequence_to_classify = "The air conditioning was a bit noisy, and had to be turned off to sleep."
candidate_labels = ['Indoor Air Quality', 'Thermal', 'Acoustic', 'Visual']
classifier(sequence_to_classify, candidate_labels)

If more than one candidate label can be correct, pass multi_label=True to calculate each class independently:

candidate_labels = ['Indoor Air Quality', 'Thermal', 'Acoustic', 'Visual']
classifier(sequence_to_classify, candidate_labels, multi_label=True)

With manual PyTorch

# pose sequence as a NLI premise and label as a hypothesis
from transformers import AutoModelForSequenceClassification, AutoTokenizer
nli_model = AutoModelForSequenceClassification.from_pretrained('Herb-Lab/LLM_housing_livability')
tokenizer = AutoTokenizer.from_pretrained('Herb-Lab/LLM_housing_livability')

premise = sequence
hypothesis = f'This example is {label}.'

# run through model pre-trained on MNLI
x = tokenizer.encode(premise, hypothesis, return_tensors='pt',
                     truncation_strategy='only_first')
logits = nli_model(x.to(device))[0]

# we throw away "neutral" (dim 1) and take the probability of
# "entailment" (2) as the probability of the label being true 
entail_contradiction_logits = logits[:,[0,2]]
probs = entail_contradiction_logits.softmax(dim=1)
prob_label_is_true = probs[:,1]