Views
No views yet
ArGTClass is a bloomz based classification model, finetuned to categorize a comprehensive spectrum
of fourteen distinct subjects that are Religion,
Finance and Economics, Politics, Medical, Cul-
ture, Sports, Science and Technology, Anthro-
pology and Sociology, Art and Literature, Edu-
cation, History, Language and Linguistics, Law,
as well as Philosophy in Arabic.
1from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
2
3tokenizer = AutoTokenizer.from_pretrained("dru-ac/ArGTClass")
4model = AutoModelForSequenceClassification.from_pretrained("dru-ac/ArGTClass")
5
6text = " .قصفت إسرائيل مستشفى المعمداني في مدينة غزة، والذي خلف مئات الشهداء والجرحى"
7
8inputs = tokenizer(text, return_tensors= 'pt')
9outputs = model(**inputs)
10ind = outputs.logits.argmax(dim=-1)[0]
11predicted_class = model.config.id2label[ind.item()]1from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
2
3tokenizer = AutoTokenizer.from_pretrained("dru-ac/ArGTClass")
4model = AutoModelForSequenceClassification.from_pretrained("dru-ac/ArGTClass", device_map = 'auto')
5
6text = " .قصفت إسرائيل مستشفى المعمداني في مدينة غزة، والذي خلف مئات الشهداء والجرحى"
7
8inputs = tokenizer(text, return_tensors= 'pt').to("cuda")
9outputs = model(**inputs)
10ind = outputs.logits.argmax(dim=-1)[0]
11predicted_class = model.config.id2label[ind.item()]1from transformers import AutoTokenizer, AutoModelForSequenceClassification
2tokenizer = AutoTokenizer.from_pretrained("dru-ac/ArGTClass")
3model = AutoModelForSequenceClassification.from_pretrained("dru-ac/ArGTClass", device_map = 'auto')
4
5classifier = pipeline("text-classification", model=model, tokenizer= tokenizer)
6
7text = " .قصفت إسرائيل مستشفى المعمداني في مدينة غزة، والذي خلف مئات الشهداء والجرحى"
8
9classifier(text)