pair_classification.py

import numpy as np

from transformers import Pipeline
from ultravox.model import ultravox_model


def softmax(outputs):
    maxes = np.max(outputs, axis=-1, keepdims=True)
    shifted_exp = np.exp(outputs - maxes)
    return shifted_exp / shifted_exp.sum(axis=-1, keepdims=True)


class PairClassificationPipeline(Pipeline):
    def _sanitize_parameters(self, **kwargs):
        preprocess_kwargs = {}
        if "second_text" in kwargs:
            preprocess_kwargs["second_text"] = kwargs["second_text"]
        return preprocess_kwargs, {}, {}

    def preprocess(self, text, second_text=None):
        return self.tokenizer(
            text, text_pair=second_text, return_tensors=self.framework
        )

    def _forward(self, model_inputs):
        return self.model(**model_inputs)

    def postprocess(self, model_outputs):
        logits = model_outputs.logits[0].numpy()
        probabilities = softmax(logits)

        best_class = np.argmax(probabilities)
        label = self.model.config.id2label[best_class]
        score = probabilities[best_class].item()
        logits = logits.tolist()
        return {"label": label, "score": score, "logits": logits}