# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("Makhmud/Kun_uz_classification")
model = AutoModelForSequenceClassification.from_pretrained("Makhmud/Kun_uz_classification")Quick Links
NLP Classification task in Uzbek language!
I used data from the kun.uz website for this task(https://lnkd.in/dZcjU8hX). This dataset contains more than 170000 news and these news are divided into 7 categories. This dataset has a imbalance problem so I have selected 4 categories("Jamiyat", "O'zbekiston", "Jahon" and "Fan va Texnika" ).
Program code: https://lnkd.in/dqraUG2Q
You can select and test a small part of news from one of the categories mentioned above from the kun.uz website.
- Downloads last month
- 7
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Makhmud/Kun_uz_classification")