claritylab/zero-shot-vanilla-gpt2

Zero-shot Vanilla GPT2

This is a modified GPT2 model. It was introduced in the Findings of ACL'23 Paper Label Agnostic Pre-training for Zero-shot Text Classification by Christopher Clarke, Yuzhao Heng, Yiping Kang, Krisztian Flautner, Lingjia Tang and Jason Mars. The code for training and evaluating this model can be found here.

Model description

This model is intended for zero-shot text classification. It was trained under the generative classification framework as a baseline with the aspect-normalized UTCD dataset.

• Finetuned from model: gpt2-medium

Usage

Install our python package:

pip install zeroshot-classifier

Then, you can use the model like this:

>>> import torch
>>> from zeroshot_classifier.models import ZsGPT2Tokenizer, ZsGPT2LMHeadModel

>>> training_strategy = 'vanilla'
>>> model_name = f'claritylab/zero-shot-{training_strategy}-gpt2'
>>> model = ZsGPT2LMHeadModel.from_pretrained(model_name)
>>> tokenizer = ZsGPT2Tokenizer.from_pretrained(model_name, form=training_strategy)

>>> text = "I'd like to have this track onto my Classical Relaxations playlist."
>>> labels = [
>>>     'Add To Playlist', 'Book Restaurant', 'Get Weather', 'Play Music', 'Rate Book', 'Search Creative Work',
>>>     'Search Screening Event'
>>> ]

>>> inputs = tokenizer(dict(text=text, label_options=labels), mode='inference-sample')
>>> inputs = {k: torch.tensor(v).unsqueeze(0) for k, v in inputs.items()}
>>> outputs = model.generate(**inputs, max_length=128)
>>> decoded = tokenizer.batch_decode(outputs, skip_special_tokens=False)[0]
>>> print(decoded)

<|question|>How is the text best described? : " Rate Book ", " Search Screening Event ", " Add To Playlist ", " Search Creative Work ", " Get Weather ", " Play Music ", " Book Restaurant "<|endoftext|><|text|>I'd like to have this track onto my Classical Relaxations playlist.<|endoftext|><|answer|>Play Media<|endoftext|>