Hi all,
I was wondering if someone got to make DeBERTa work on NLI task using the pre-trained model available in Hugging Face?
When running this code, the contradiction is always empty (although entailment and neutral score are populated).
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
if __name__ == '__main__':
max_length = 256
premise = "Two women are embracing while holding to go packages."
hypothesis = "The men are fighting outside a deli."
hg_model_hub_name = "microsoft/deberta-large"
# hg_model_hub_name = "microsoft/deberta-base"
tokenizer = AutoTokenizer.from_pretrained(hg_model_hub_name)
model = AutoModelForSequenceClassification.from_pretrained(hg_model_hub_name)
tokenized_input_seq_pair = tokenizer.encode_plus(premise, hypothesis,
max_length=max_length,
return_token_type_ids=True, truncation=True)
input_ids = torch.Tensor(tokenized_input_seq_pair['input_ids']).long().unsqueeze(0)
# remember bart doesn't have 'token_type_ids', remove the line below if you are using bart.
token_type_ids = torch.Tensor(tokenized_input_seq_pair['token_type_ids']).long().unsqueeze(0)
attention_mask = torch.Tensor(tokenized_input_seq_pair['attention_mask']).long().unsqueeze(0)
outputs = model(input_ids,
attention_mask=attention_mask,
token_type_ids=token_type_ids,
labels=None)
# Note:
# "id2label": {
# "0": "entailment",
# "1": "neutral",
# "2": "contradiction"
# },
predicted_probability = torch.softmax(outputs[0], dim=1)[0].tolist() # batch_size only one
print("Premise:", premise)
print("Hypothesis:", hypothesis)
print("Entailment:", predicted_probability[0])
print("Neutral:", predicted_probability[1])
print("Contradiction:", predicted_probability[2])