metadata

language:
  - en
tags:
  - text-classification
  - mednli
  - text-generation
datasets:
  - pubmed
  - pmc/open_access

SciFive Pubmed+PMC Large on MedNLI

Introduction

Finetuned SciFive Pubmed+PMC Large model achieved state-of-the-art results on MedNLI (Medical Natural Language Inference)

Paper: SciFive: a text-to-text transformer model for biomedical literature

Authors: Long N. Phan, James T. Anibal, Hieu Tran, Shaurya Chanana, Erol Bahadroglu, Alec Peltekian, Grégoire Altan-Bonnet

How to use

For more details, do check out our Github repo.

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("razent/SciFive-large-Pubmed_PMC-MedNLI")  
model = AutoModelForSeq2SeqLM.from_pretrained("razent/SciFive-large-Pubmed_PMC-MedNLI")

sentence = "Identification of APC2 , a homologue of the adenomatous polyposis coli tumour suppressor ."
text =  "mednli: " + sentence + " </s>"

encoding = tokenizer.encode_plus(text, pad_to_max_length=True, return_tensors="pt")
input_ids, attention_masks = encoding["input_ids"].to("cuda"), encoding["attention_mask"].to("cuda")

outputs = model.generate(
    input_ids=input_ids, attention_mask=attention_masks,
    max_length=8,
    early_stopping=True
)

for output in outputs:
    line = tokenizer.decode(output, skip_special_tokens=True, clean_up_tokenization_spaces=True)
    print(line)