lamsytan's picture
Update README.md
b179afb verified
metadata
language:
  - vi
base_model:
  - VietAI/vit5-base

A model fine-tuned for sentiment analysis based on VietAI/vit5-base.

Labels:

  • NEG: Negative
  • POS: Positive
  • NEU: Neutral

Dataset: Comments on Shoppe (https://shopee.vn/)

Usage

import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("lamsytan/sentiment-analysis-base-phobert")
model = AutoModelForSequenceClassification.from_pretrained("lamsytan/sentiment-analysis-base-phobert")

sentence = "Áo đẹp lắm nhá lần sau sẽ ghé tiếp ạ"

inputs = tokenizer(sentence, return_tensors="pt", padding=True, truncation=True)

with torch.no_grad():
    outputs = model(**inputs)
    logits = outputs.logits
    probabilities = torch.softmax(logits, dim=-1)

print(probabilities.tolist())
    # Output:
    # [[0.010827462188899517, 0.9538241624832153, 0.035348404198884964]]
    #         ^                         ^                  ^