defunct-datasets/the_pile_openwebtext2
Updated • 224 • 15
How to use nthngdy/headless-bert-bs64-owt2 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("token-classification", model="nthngdy/headless-bert-bs64-owt2") # Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("nthngdy/headless-bert-bs64-owt2")
model = AutoModelForMaskedLM.from_pretrained("nthngdy/headless-bert-bs64-owt2")This model is a bert-base architecture trained on OpenWebText-2 using the Contrastive Weight Tying objective.
BibTeX:
@misc{godey2023headless,
title={Headless Language Models: Learning without Predicting with Contrastive Weight Tying},
author={Nathan Godey and Éric de la Clergerie and Benoît Sagot},
year={2023},
eprint={2309.08351},
archivePrefix={arXiv},
primaryClass={cs.CL}
}