Structured Pruning Learns Compact and Accurate Models
Paper • 2204.00408 • Published • 1
How to use princeton-nlp/CoFi-SQuAD-s93 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("question-answering", model="princeton-nlp/CoFi-SQuAD-s93") # Load model directly
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
tokenizer = AutoTokenizer.from_pretrained("princeton-nlp/CoFi-SQuAD-s93")
model = AutoModelForQuestionAnswering.from_pretrained("princeton-nlp/CoFi-SQuAD-s93")YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
This is a model checkpoint for "Structured Pruning Learns Compact and Accurate Models". The model is pruned from bert-base-uncased to a 93% sparsity on dataset SQuAD 1.1. Please go to our repository for more details on how to use the model for inference. Note that you would have to use the model class specified in our repository to load the model.