from transformers import AutoTokenizer, pipeline
model = "mjwong/drama-base-xnli-anli"
classifier = pipeline("zero-shot-classification",
                      model=model)

You can then use this pipeline to classify sequences into any of the class names you specify.

python

sequence_to_classify = "one day I will see the world"
candidate_labels = ['travel', 'cooking', 'dancing']
classifier(sequence_to_classify, candidate_labels)

If more than one candidate label can be correct, pass multi_class=True to calculate each class independently:

python

candidate_labels = ['travel', 'cooking', 'dancing', 'exploration']
classifier(sequence_to_classify, candidate_labels, multi_class=True)

With manual PyTorch

The model can also be applied on NLI tasks like so:

python

import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification

# device = "cuda:0" or "cpu"
device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")

model_name = "mjwong/drama-base-xnli-anli"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

premise = "But I thought you'd sworn off coffee."
hypothesis = "I thought that you vowed to drink more coffee."

input = tokenizer(premise, hypothesis, truncation=True, return_tensors="pt")
output = model(input["input_ids"].to(device))
prediction = torch.softmax(output["logits"][0], -1).tolist()
label_names = ["entailment", "neutral", "contradiction"]
prediction = {name: round(float(pred) * 100, 2) for pred, name in zip(prediction, label_names)}
print(prediction)

Eval results

The model was evaluated using the XNLI test sets on 15 languages: English (en), Arabic (ar), Bulgarian (bg), German (de), Greek (el), Spanish (es), French (fr), Hindi (hi), Russian (ru), Swahili (sw), Thai (th), Turkish (tr), Urdu (ur), Vietnam (vi) and Chinese (zh). The metric used is accuracy.

Datasets	en	ar	bg	de	el	es	fr	hi	ru	sw	th	tr	ur	vi	zh
drama-base-xnli-anli	0.788	0.689	0.708	0.715	0.696	0.732	0.737	0.647	0.711	0.636	0.676	0.664	0.588	0.708	0.710
drama-large-xnli-anli	0.799	0.698	0.730	0.721	0.717	0.754	0.754	0.649	0.718	0.652	0.678	0.656	0.594	0.719	0.719

The model was also evaluated using the dev sets for MultiNLI and test sets for ANLI. The metric used is accuracy.

Datasets	mnli_dev_m	mnli_dev_mm	anli_test_r1	anli_test_r2	anli_test_r3
drama-base-xnli-anli	0.781	0.787	0.500	0.420	0.440
drama-large-xnli-anli	0.794	0.796	0.534	0.446	0.452

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1

Framework versions

Transformers 4.49.0
Pytorch 2.6.0+cu124
Datasets 3.2.0
Tokenizers 0.21.0