Drama Large Xnli Anli

🚀 drama-large-xnli-anli

This model is a fine - tuned version of facebook/drama-large on the XNLI and ANLI dataset. It enables zero - shot classification across multiple languages, offering a powerful solution for various natural language processing tasks.

✨ Features

• Multilingual Support: Supports multiple languages including English, Arabic, Bulgarian, German, Greek, Spanish, French, Hindi, Russian, Swahili, Thai, Turkish, Urdu, Vietnamese, and Chinese.
• Zero - Shot Classification: Can perform zero - shot classification tasks effectively.
• Fine - Tuned on Diverse Datasets: Fine - tuned on XNLI and ANLI datasets, enhancing its performance on natural language inference tasks.

📦 Installation

This section is skipped as no specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

The model can be loaded with the zero - shot classification pipeline like so:

from transformers import AutoTokenizer, pipeline
model = "mjwong/drama-large-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.

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:

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

Advanced Usage

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

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-large-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)

📚 Documentation

Model description

DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers. Xueguang Ma, Xi Victoria Lin, Barlas Oguz, Jimmy Lin, Wen - tau Yih, Xilun Chen, arXiv 2025

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.

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

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

🔧 Technical Details

This section is skipped as no specific technical implementation details are provided in the original document.

📄 License

The license for this model is cc - by - nc - 4.0.

Additional Information