Model Summary

This model is a fine-tuned version of vinai/phobert-base-v2 for the Vietnamese Natural Language Inference (NLI) task. It determines whether a premise sentence entails, contradicts, or is neutral to a hypothesis sentence.

Model Details

Model Description

• Developed by: Nguyễn Vĩnh Hưng
• Model type: transformer-based text classification
• Language(s) (NLP): Vietnamese
• Finetuned from model: vinai/phobert-base-v2

How To Use

# Install necessary libraries
# !pip install transformers torch

from transformers import pipeline

model_name = "lizNguyen235/phobert-nli-vi"
classifier = pipeline("zero-shot-classification", model=model_name)

sequence_to_classify = "Apple vừa ra mắt iPhone 15 với cổng sạc USB-C."
candidate_labels = ['công nghệ', 'ẩm thực', 'chính trị', 'thể thao']

vietnamese_template = "Chủ đề của câu này là {}."

result = classifier(
    sequence_to_classify, 
    candidate_labels,
    hypothesis_template=vietnamese_template
)