README.md

metadata

language: fa
pipeline_tag: text-classification
library_name: transformers

QomSSLab/verdict_classifier_v1

This repository hosts a sequence-classification head trained for text classification.

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline

model_id = "QomSSLab/verdict_classifier_v1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForSequenceClassification.from_pretrained(model_id)
classifier = pipeline("text-classification", model=model, tokenizer=tokenizer)

text = "مثال از یک ورودی فارسی"
print(classifier(text))

Labels

• 1
• 2
• 3
• 4

Metrics

Validation Metrics

• Precision: 0.9523
• Recall: 0.9514
• F1: 0.9514
• Accuracy: 0.9514

Per-label Breakdown

Label	Precision	Recall	F1	Support
1	0.9643	0.9818	0.9730	110
2	0.9903	0.9273	0.9577	110
3	0.9304	0.9727	0.9511	110
4	0.8750	0.8750	0.8750	40