VanillaKD-Pretrain-Qwen-200M is a 200M model with Qwen achitecture pre-trained with vanilla token-level knowledge distillation on
the Pile for 50B tokens. The teacher model is
Qwen1.5-1.8B.
We also open-source the tokenized
pre-training corpus for reproducibility.
MiniPLM models achieves better performance given the same computation and scales well across model sizes:
1@article{miniplm,
2 title={MiniPLM: Knowledge Distillation for Pre-Training Language Models},
3 author={Yuxian Gu and Hao Zhou and Fandong Meng and Jie Zhou and Minlie Huang},
4 journal={arXiv preprint arXiv:2410.17215},
5 year={2024}
6}
