Fix token type ids

[xenova]

A fix needed for #497, where token type ids were not correctly chosen from the post-processor template.

closes #497

Example code:

import { AutoTokenizer, AutoModelForSequenceClassification } from '@xenova/transformers';

const model_id = 'Xenova/ms-marco-TinyBERT-L-2-v2';

const model = await AutoModelForSequenceClassification.from_pretrained(model_id);
const tokenizer = await AutoTokenizer.from_pretrained(model_id);

const features = tokenizer(
    ['How many people live in Berlin?', 'How many people live in Berlin?'],
    {
        text_pair: [
            'Berlin has a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers.',
            'New York City is famous for the Metropolitan Museum of Art.',
        ],
        padding: true,
        truncation: true,
    }
)

const scores = await model(features)
console.log(scores);
// quantized:   [ 7.210887908935547, -11.559350967407227 ]
// unquantized: [ 7.235750675201416, -11.562294006347656 ]

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.