En-ViMedNER
Collection
English–Vietnamese biomedical NER dataset and finetuned models (MT, NER, direct-trans-ner). • 13 items • Updated
umt5-base-en-vimedner-ner-vi
google/umt5-base 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/umt5-base-en-vimedner-ner-vi"
tok = AutoTokenizer.from_pretrained(repo)
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, max_new_tokens=256)
print(tok.decode(outputs[0], skip_special_tokens=True))
Related
- English NER:
nhuvo/umt5-base-en-vimedner-ner-en
- Downloads last month
- 26
Model tree for nhuvo/umt5-base-en-vimedner-ner-vi
Base model
google/umt5-base