Quantization made by Richard Erkhov.
MiniPLM-llama3.1-212M is a 212M model with the
LLaMA3.1 achitecture pre-trained from scratch on
the Pile using the MiniPLM knowledge distillation framework with the
offcial Qwen1.5-1.8B as the teacher model.
This model shows the flexibility of the MiniPLM framework in conducting knowledge distillation across model families.
We also open-source the
pre-training corpus refined by Difference Sampling in MiniPLM 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}
