Back to all models
question-answering mask_token: <mask>
Query this model
馃敟 This model is currently loaded and running on the Inference API. 鈿狅笍 This model could not be loaded by the inference API. 鈿狅笍 This model can be loaded on the Inference API on-demand.
JSON Output
API endpoint  

鈿★笍 Upgrade your account to access the Inference API

							curl -X POST \
-H "Authorization: Bearer YOUR_ORG_OR_USER_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"question": "Where does she live?", "context": "She lives in Berlin."}' \
Share Copied link to clipboard

Monthly model downloads

valhalla/bart-large-finetuned-squadv1 valhalla/bart-large-finetuned-squadv1
last 30 days



Contributed by

valhalla Suraj Patil
15 models

How to use this model directly from the 馃/transformers library:

Copy to clipboard
from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("valhalla/bart-large-finetuned-squadv1") model = AutoModelForQuestionAnswering.from_pretrained("valhalla/bart-large-finetuned-squadv1")

BART-LARGE finetuned on SQuADv1

This is bart-large model finetuned on SQuADv1 dataset for question answering task

Model details

BART was propsed in the paper BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. BART is a seq2seq model intended for both NLG and NLU tasks.

To use BART for question answering tasks, we feed the complete document into the encoder and decoder, and use the top hidden state of the decoder as a representation for each word. This representation is used to classify the token. As given in the paper bart-large achives comparable to ROBERTa on SQuAD. Another notable thing about BART is that it can handle sequences with upto 1024 tokens.

Param #Value
encoder layers 12
decoder layers 12
hidden size 4096
num attetion heads 16
on disk size 1.63GB

Model training

This model was trained on google colab v100 GPU. You can find the fine-tuning colab here Open In Colab.


The results are actually slightly worse than given in the paper. In the paper the authors mentioned that bart-large achieves 88.8 EM and 94.6 F1

Metric #Value
EM 86.8022
F1 92.7342

Model in Action 馃殌

from transformers import BartTokenizer, BartForQuestionAnswering
import torch

tokenizer = BartTokenizer.from_pretrained('valhalla/bart-large-finetuned-squadv1')
model = BartForQuestionAnswering.from_pretrained('valhalla/bart-large-finetuned-squadv1')

question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
encoding = tokenizer(question, text, return_tensors='pt')
input_ids = encoding['input_ids']
attention_mask = encoding['attention_mask']

start_scores, end_scores = model(input_ids, attention_mask=attention_mask, output_attentions=False)[:2]

all_tokens = tokenizer.convert_ids_to_tokens(input_ids[0])
answer = ' '.join(all_tokens[torch.argmax(start_scores) : torch.argmax(end_scores)+1])
answer = tokenizer.convert_tokens_to_ids(answer.split())
answer = tokenizer.decode(answer)
#answer => 'a nice puppet' 

Created with 鉂わ笍 by Suraj Patil Github icon Twitter icon