Back to all models
translation mask_token:
Query this model
πŸ”₯ This model is currently loaded and running on the Inference API. ⚠️ This model could not be loaded by the inference API. ⚠️ This model can be loaded on the Inference API on-demand.
JSON Output
API endpoint  

⚑️ Upgrade your account to access the Inference API

Share Copied link to clipboard

Monthly model downloads

tuner007/t5_abs_qa tuner007/t5_abs_qa
278 downloads
last 30 days

pytorch

tf

Contributed by

tuner007 Arpit Rajauria
3 models

How to use this model directly from the πŸ€—/transformers library:

			
Copy to clipboard
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("tuner007/t5_abs_qa") model = AutoModelForSeq2SeqLM.from_pretrained("tuner007/t5_abs_qa")

T5 for abstractive question-answering

This is T5-base model fine-tuned for abstractive QA using text-to-text approach

Model training

This model was trained on colab TPU with 35GB RAM for 2 epochs

Model in Action πŸš€

from transformers import AutoModelWithLMHead, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("tuner007/t5_abs_qa")
model = AutoModelWithLMHead.from_pretrained("tuner007/t5_abs_qa")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = model.to(device)

def get_answer(question, context):
input_text = "context: %s <question for context: %s </s>" % (context,question)
features = tokenizer([input_text], return_tensors='pt')
out = model.generate(input_ids=features['input_ids'].to(device), attention_mask=features['attention_mask'].to(device))
return tokenizer.decode(out[0])

Example 1: Answer available

context = "In Norse mythology, Valhalla is a majestic, enormous hall located in Asgard, ruled over by the god Odin."
question = "What is Valhalla?"
get_answer(question, context)
# output: 'It is a hall of worship ruled by Odin.'

Example 2: Answer not available

context = "In Norse mythology, Valhalla is a majestic, enormous hall located in Asgard, ruled over by the god Odin."
question = "What is Asgard?"
get_answer(question, context)
# output: 'No answer available in context.'

Created by Arpit Rajauria Twitter icon