from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

repo = "nhuvo/nllb-600m-en-vimedner-ner-en"
tok = AutoTokenizer.from_pretrained(repo, src_lang="eng_Latn")
model = AutoModelForSeq2SeqLM.from_pretrained(repo)

prefix = "recognize English named entities: "
text = "Patients with type 2 diabetes mellitus were enrolled."
inputs = tok(prefix + text, return_tensors="pt")
outputs = model.generate(
    **inputs,
    forced_bos_token_id=tok.convert_tokens_to_ids("eng_Latn"),
    max_new_tokens=256,
)
print(tok.batch_decode(outputs, skip_special_tokens=True)[0])

Vietnamese NER: nhuvo/nllb-600m-en-vimedner-ner-vi

nhuvo/nllb-600m-en-vimedner-ner-en

nllb-600m-en-vimedner-ner-en

Usage

Related

nhuvo/
nllb-600m-en-vimedner-ner-en