README.md

metadata

language: vi
tags:
  - spam-detection
  - vietnamese
  - phobert
license: apache-2.0
datasets:
  - visolex/ViSpamReviews
metrics:
  - accuracy
  - f1
model-index:
  - name: phobert-spam-binary
    results:
      - task:
          type: text-classification
          name: Spam Detection (Binary)
        dataset:
          name: ViSpamReviews
          type: custom
        metrics:
          - name: Accuracy
            type: accuracy
            value: <INSERT_ACCURACY>
          - name: F1 Score
            type: f1
            value: <INSERT_F1_SCORE>
base_model:
  - vinai/phobert-base
pipeline_tag: text-classification

PhoBERT-Spam-Binary

Fine-tuned from vinai/phobert-base on ViSpamReviews (binary).

• Task: Binary classification (0 = non-spam, 1 = spam)

• Dataset: ViSpamReviews

• Hyperparameters

  • Batch size: 32
  • LR: 3e-5
  • Epochs: 100
  • Max seq len: 256

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("visolex/phobert-spam-binary")
model = AutoModelForSequenceClassification.from_pretrained("visolex/phobert-spam-binary")

text = "Đánh giá ảo hoàn toàn!"
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=256)
pred = model(**inputs).logits.argmax(dim=-1).item()
print("Spam" if pred==1 else "Non-spam")