nfliu

/

MiniLMv2-L6-H768-distilled-from-RoBERTa-Large_boolq

like 0

Added to readme:

import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer

model = AutoModelForSequenceClassification.from_pretrained("nfliu/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large_boolq")
tokenizer = AutoTokenizer.from_pretrained("nfliu/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large_boolq")

# Each example is a (question, context) pair.
examples = [
    ("Lake Tahoe is in California", "Lake Tahoe is a popular tourist spot in California."),
    ("Water is wet", "Contrary to popular belief, water is not wet.")
]

encoded_input = tokenizer(examples, padding=True, truncation=True, return_tensors="pt")

with torch.no_grad():
    model_output = model(**encoded_input)
    probabilities = torch.softmax(model_output.logits, dim=-1).cpu().tolist()

probability_no = [round(prob[0], 2) for prob in probabilities]
probability_yes = [round(prob[1], 2) for prob in probabilities]

for example, p_no, p_yes in zip(examples, probability_no, probability_yes):
    print(f"Question: {example[0]}")
    print(f"Context: {example[1]}")
    print(f"p(No | question, context): {p_no}")
    print(f"p(Yes | question, context): {p_yes}")
    print()