# Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("nowalab/nepali-bert-npvec1")
model = AutoModelForMaskedLM.from_pretrained("nowalab/nepali-bert-npvec1", device_map="auto")Quick Links
We are releasing the first BERT model trained on monolingual text for Nepali. Please refer our paper NPVec1: Word Embeddings for Nepali - Construction and Evaluation to get details on its construction and evaluation.
- Downloads last month
- 6
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="nowalab/nepali-bert-npvec1")