47 lines
1.7 KiB
Markdown
47 lines
1.7 KiB
Markdown
---
|
|
library_name: transformers
|
|
license: apache-2.0
|
|
datasets:
|
|
- monology/pile-uncopyrighted
|
|
- MiniLLM/pile-diff_samp-qwen_1.8B-qwen_104M-r0.5
|
|
language:
|
|
- en
|
|
metrics:
|
|
- accuracy
|
|
pipeline_tag: text-generation
|
|
---
|
|
|
|
# MinPLM-Qwen-200M
|
|
|
|
[paper](https://arxiv.org/abs/2410.17215) | [code](https://github.com/thu-coai/MiniPLM)
|
|
|
|
**MiniPLM-Qwen-200M** is a 200M model with Qwen achitecture pre-trained from scratch on [the Pile](https://huggingface.co/datasets/monology/pile-uncopyrighted) using the MiniPLM knowledge distillation framework with the [offcial Qwen1.5-1.8B](https://huggingface.co/Qwen/Qwen1.5-1.8B) as the teacher model.
|
|
|
|
We also open-source the [pre-training corpus](https://huggingface.co/datasets/MiniLLM/pile-diff_samp-qwen_1.8B-qwen_104M-r0.5) refined by Difference Sampling in MiniPLM for reproducibility.
|
|
|
|
<p align='left'>
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/624ac662102fcdff87be51b9/2BqT0NgkmIXYlktovw9kG.png" width="1000">
|
|
</p>
|
|
|
|
## Evaluation
|
|
|
|
MiniPLM models achieves better performance given the same computation and scales well across model sizes:
|
|
|
|
<p align='left'>
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/624ac662102fcdff87be51b9/EOYzajQcwQFT5PobqL3j0.png" width="1000">
|
|
</p>
|
|
|
|
## Baseline Models
|
|
+ [Conventional Pre-Training](https://huggingface.co/MiniLLM/Pretrain-Qwen-200M)
|
|
+ [VanillaKD](https://huggingface.co/MiniLLM/VanillaKD-Pretrain-Qwen-200M)
|
|
|
|
## Citation
|
|
|
|
```bibtex
|
|
@article{miniplm,
|
|
title={MiniPLM: Knowledge Distillation for Pre-Training Language Models},
|
|
author={Yuxian Gu and Hao Zhou and Fandong Meng and Jie Zhou and Minlie Huang},
|
|
journal={arXiv preprint arXiv:2410.17215},
|
|
year={2024}
|
|
}
|
|
``` |