Model Card
This model is pretrained Based model.
As a quality reference, we include a pretrained Mamba model provided here: https://huggingface.co/hazyresearch/mamba-1b-50b and a pretrained attention (Llama architecture) model provided here: https://huggingface.co/hazyresearch/attn-1b-50bn
All three checkpoints are pretrained on 50Bn tokens of the Pile in the exact same data order using next token prediction.
A WandB report for training is here: https://api.wandb.ai/links/hazy-research/ggo9rst2
Model Sources
The model implementation and training code that produced the model are provided here: https://github.com/HazyResearch/based
Uses
The purpose of this work is to evaluate the language modeling quality of a new efficient architecture, Based.
We include a series of benchmarks that you can use to evaluate quality:
- FDA: https://huggingface.co/datasets/hazyresearch/based-fda
- SWDE: https://huggingface.co/datasets/hazyresearch/based-swde
- SQUAD: https://huggingface.co/datasets/hazyresearch/based-squad
Citation
Please consider citing this paper if you use our work:
@article{arora2024simple,
title={Simple linear attention language models balance the recall-throughput tradeoff},
author={Arora, Simran and Eyuboglu, Sabri and Zhang, Michael and Timalsina, Aman and Alberti, Silas and Zinsley, Dylan and Zou, James and Rudra, Atri and Ré, Christopher},
journal={arXiv:2402.18668},
year={2024}
}
Please reach out to [email protected], [email protected], and [email protected] with questions.
- Downloads last month
- 124