Mpnet Base Snli Mnli

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

This is a cross-attention NLI model designed for zero-shot and few-shot text classification. It leverages the power of the mpnet-base architecture, trained with the code from here on the SNLI and MNLI datasets.

✨ Features

• Zero-shot and Few-shot Capability: Enables text classification with limited or no labeled data.
• Cross-attention Mechanism: Enhances the model's ability to capture relationships between text pairs.
• Trained on SNLI and MNLI: Utilizes high-quality natural language inference datasets for robust performance.

📦 Installation

No specific installation steps are provided in the original README. However, you need to have the transformers and torch libraries installed to use the model. You can install them using pip:

pip install transformers torch numpy

💻 Usage Examples

Basic Usage

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

model = AutoModelForSequenceClassification.from_pretrained("symanto/mpnet-base-snli-mnli")
tokenizer = AutoTokenizer.from_pretrained("symanto/mpnet-base-snli-mnli")

input_pairs = [("I like this pizza.", "The sentence is positive."), ("I like this pizza.", "The sentence is negative.")]
inputs = tokenizer(["</s></s>".join(input_pair) for input_pair in input_pairs], return_tensors="pt")
logits = model(**inputs).logits
probs =  torch.softmax(logits, dim=1).tolist()
print("probs", probs)
np.testing.assert_almost_equal(probs, [[0.86, 0.14, 0.00], [0.16, 0.15, 0.69]], decimal=2)

📚 Documentation

The model uses the AutoModelForSequenceClassification and AutoTokenizer from the transformers library. The input text pairs are tokenized and passed through the model to obtain logits, which are then converted to probabilities using the softmax function.

📄 License

No license information is provided in the original README.

📦 Dataset and Tags