Views
No views yet
1## BSL-1.7B
2
3[paper](https://arxiv.org/abs/2410.07064) | [code](https://github.com/microsoft/LMOps/tree/main/data_selection)
4
5**BSL-1.7B** is a 1.7B model with [Mistral](https://arxiv.org/abs/2310.06825) achitecture pre-trained from scratch on the CC split of [Redpajama](https://github.com/togethercomputer/RedPajama-Data).
6
7**It is used as the baseline for [PDS-1.7B](https://huggingface.co/Data-Selection/PDS-1.7B).**
8
9### Evaluation
10
11PDS-selected data improves the performance of language models pre-trained from scratch and saves pre-training comptation. The improvement scales up to large model sizes.
12
13<p align='left'>
14 <img src="https://cdn-uploads.huggingface.co/production/uploads/624ac662102fcdff87be51b9/6undIr37d10qD73TDiPDK.png" width="600">
15</p>
16
17### Citation
18
19```bibtex
20@article{gu2024data,
21 title={Data Selection via Optimal Control for Language Models},
22 author={Gu, Yuxian and Dong, Li and Wang, Hongning and Hao, Yaru and Dong, Qingxiu and Wei, Furu and Huang, Minlie},
23 journal={arXiv preprint arXiv:2410.07064},
24 year={2024}
25}