aryasuneesh-quilr/hybrid-intent-crossencoder-miniLM2-L6-H768

user_input [SEP] intent_description

import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification

model_id  = "aryasuneesh-quilr/hybrid-intent-crossencoder-miniLM2-L6-H768"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model     = AutoModelForSequenceClassification.from_pretrained(model_id)
model.eval()

def score(user_input: str, intent_description: str) -> float:
    pair = f"{user_input} [SEP] {intent_description}"
    enc  = tokenizer(pair, return_tensors="pt", truncation=True, max_length=256)
    with torch.no_grad():
        logits = model(**enc).logits
    return torch.softmax(logits, dim=1)[0, 1].item()   # P(match)

# Example
s = score(
    "Our AWS_SECRET_ACCESS_KEY was found in a public repo",
    "Identify exposure of authentication credentials or API keys"
)
print(f"Match probability: {s:.4f}")   # use threshold 0.8226 for best F1