Xlm Roberta Base Snli Mnli Anli Xnli

🚀 Cross-attention NLI Model for Zero-shot and Few-shot Text Classification

A cross-attention NLI model designed for zero-shot and few-shot text classification, offering efficient and accurate classification across multiple languages.

🚀 Quick Start

This is a cross-attention NLI model trained for zero-shot and few-shot text classification. The base model is xlm-roberta-base, which was trained using the code from here on SNLI, MNLI, ANLI and XNLI.

✨ Features

• Multilingual Support: Supports multiple languages including Arabic, Bulgarian, German, Greek, English, Spanish, French, Russian, Thai, Turkish, Urdu, Vietnamese, Chinese, and multilingual scenarios.
• Zero-shot and Few-shot Classification: Enables classification tasks with little to no labeled data.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import AutoModelForSequenceClassification, AutoTokenizer
import torch
import numpy as np

model = AutoModelForSequenceClassification.from_pretrained("symanto/xlm-roberta-base-snli-mnli-anli-xnli")
tokenizer = AutoTokenizer.from_pretrained("symanto/xlm-roberta-base-snli-mnli-anli-xnli")

input_pairs = [
               ("I like this pizza.", "The sentence is positive."),
               ("I like this pizza.", "The sentence is negative."),
               ("I mag diese Pizza.", "Der Satz ist positiv."),
               ("I mag diese Pizza.", "Der Satz ist negativ."),
               ("Me gusta esta pizza.", "Esta frase es positivo."),
               ("Me gusta esta pizza.", "Esta frase es negativo."),
]
inputs = tokenizer(input_pairs, truncation="only_first", return_tensors="pt", padding=True)
logits = model(**inputs).logits
probs = torch.softmax(logits, dim=1)
probs = probs[..., [0]].tolist()
print("probs", probs)
np.testing.assert_almost_equal(probs, [[0.83], [0.04], [1.00], [0.00], [1.00], [0.00]], decimal=2)

📚 Documentation

Model Information