En-ViMedNER
Collection
English–Vietnamese biomedical NER dataset and finetuned models (MT, NER, direct-trans-ner). • 15 items • Updated
nllb-600m-en-vimedner-ner-vi
facebook/nllb-200-distilled-600M fine-tuned for Vietnamese biomedical NER (plain text → inline tagged text) on En-ViMedNER.
Dataset details, label inventory, splits, and citation: nhuvo/En-ViMedNER.
Usage
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
repo = "nhuvo/nllb-600m-en-vimedner-ner-vi"
tok = AutoTokenizer.from_pretrained(repo, src_lang="vie_Latn")
model = AutoModelForSeq2SeqLM.from_pretrained(repo)
prefix = "recognize Vietnamese named entities: "
text = "Bệnh nhân đái tháo đường típ 2 được tuyển vào nghiên cứu."
inputs = tok(prefix + text, return_tensors="pt")
outputs = model.generate(
**inputs,
forced_bos_token_id=tok.convert_tokens_to_ids("vie_Latn"),
max_new_tokens=256,
)
print(tok.batch_decode(outputs, skip_special_tokens=True)[0])
Related
- English NER:
nhuvo/nllb-600m-en-vimedner-ner-en
- Downloads last month
- 15
Model tree for nhuvo/nllb-600m-en-vimedner-ner-vi
Base model
facebook/nllb-200-distilled-600M