35 lines
2.1 KiB
Markdown
35 lines
2.1 KiB
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
datasets:
|
||
|
|
- datajuicer/redpajama-wiki-refined-by-data-juicer
|
||
|
|
- datajuicer/redpajama-arxiv-refined-by-data-juicer
|
||
|
|
- datajuicer/redpajama-c4-refined-by-data-juicer
|
||
|
|
- datajuicer/redpajama-book-refined-by-data-juicer
|
||
|
|
- datajuicer/redpajama-cc-2019-30-refined-by-data-juicer
|
||
|
|
- datajuicer/redpajama-cc-2020-05-refined-by-data-juicer
|
||
|
|
- datajuicer/redpajama-cc-2021-04-refined-by-data-juicer
|
||
|
|
- datajuicer/redpajama-cc-2022-05-refined-by-data-juicer
|
||
|
|
- datajuicer/redpajama-cc-2023-06-refined-by-data-juicer
|
||
|
|
- datajuicer/redpajama-pile-stackexchange-refined-by-data-juicer
|
||
|
|
- datajuicer/redpajama-stack-code-refined-by-data-juicer
|
||
|
|
- datajuicer/the-pile-nih-refined-by-data-juicer
|
||
|
|
- datajuicer/the-pile-europarl-refined-by-data-juicer
|
||
|
|
- datajuicer/the-pile-philpaper-refined-by-data-juicer
|
||
|
|
- datajuicer/the-pile-pubmed-abstracts-refined-by-data-juicer
|
||
|
|
- datajuicer/the-pile-pubmed-central-refined-by-data-juicer
|
||
|
|
- datajuicer/the-pile-freelaw-refined-by-data-juicer
|
||
|
|
- datajuicer/the-pile-hackernews-refined-by-data-juicer
|
||
|
|
- datajuicer/the-pile-uspto-refined-by-data-juicer
|
||
|
|
---
|
||
|
|
## News
|
||
|
|
Our first data-centric LLM competition begins! Please visit the competition's official websites, **FT-Data Ranker** ([1B Track](https://tianchi.aliyun.com/competition/entrance/532157), [7B Track](https://tianchi.aliyun.com/competition/entrance/532158)), for more information.
|
||
|
|
## Introduction
|
||
|
|
This is a reference LLM from [Data-Juicer](https://github.com/alibaba/data-juicer).
|
||
|
|
|
||
|
|
The model architecture is LLaMA-1.3B and we adopt the [OpenLLaMA](https://github.com/openlm-research/open_llama) implementation.
|
||
|
|
The model is pre-trained on 150B tokens of Data-Juicer's refined RedPajama and Pile.
|
||
|
|
It achieves an average score of 34.21 over 16 HELM tasks, beating Falcon-1.3B (trained on 350B tokens from RefinedWeb), Pythia-1.4B (trained on 300B tokens from original Pile) and Open-LLaMA-1.3B (trained on 150B tokens from original RedPajama and Pile).
|
||
|
|
|
||
|
|
For more details, please refer to our [paper](https://arxiv.org/abs/2309.02033).
|
||
|
|
|
||
|
|
|