umt5-base-en-vimedner-mt-en2vi

google/umt5-base fine-tuned for English → Vietnamese biomedical translation on En-ViMedNER.

Dataset details, splits, and citation: nhuvo/En-ViMedNER.

Usage

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

repo = "nhuvo/umt5-base-en-vimedner-mt-en2vi"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForSeq2SeqLM.from_pretrained(repo)

text = "Patients with type 2 diabetes mellitus were enrolled."
inputs = tok(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tok.decode(outputs[0], skip_special_tokens=True))

Related

• Pair model (VI→EN): nhuvo/umt5-base-en-vimedner-mt-vi2en