from transformers import AutoTokenizer, AutoModelForTokenClassification
import numpy as np

# match tag
id2tag = {0:'O', 1:'B_MT', 2:'I_MT'}

# load model & tokenizer
MODEL_NAME = 'MDDDDR/dmis_lab_biobert_v1.1_NER'

model = AutoModelForTokenClassification.from_pretrained(MODEL_NAME)
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)

# prepare input
text = 'mental disorder can also contribute to the development of diabetes through various mechanism including increased stress, poor self care behavior, and adverse effect on glucose metabolism.'
tokenized = tokenizer(text, return_tensors='pt')

# forward pass
output = model(**tokenized)

# result
preds = np.argmax(output[0].cpu().detach().numpy(), axis=2)[0][1:-1]

# check preds
for txt, pred in zip(tokenizer.tokenize(text), preds):
    print("{}\t{}".format(id2tag[pred], txt))
    # B_MT mental 
    # B_MT disorder
    # O	can
    # O	also
    # O	contribute
    # O	to
    # O	the
    # B_MT	development
    # O	of
    # B_MT	diabetes
    # O	through
    # O	various
    # B_MT	mechanism
    # O	including
    # O	increased
    # B_MT	stress
    # O	,
    # O	poor
    # B_MT	self
    # B_MT	care
    # B_MT	behavior
    # O	,
    # O	and
    # B_MT	adverse
    # I_MT	effect
    # O	on
    # B_MT	glucose
    # B_MT	metabolism
    # O	.

Framework versions

transformers : 4.39.1
torch : 2.1.0+cu121
datasets : 2.18.0
tokenizers : 0.15.2
numpy : 1.20.0