LLaMA Pro: Progressive LLaMA with Block Expansion (Paper Explained)

Note: The H800 is a variant of the H100 for the Chinese market

OUTLINE:
0:00 - Introduction
5:30 - Adding new blocks to LLaMA
15:00 - Block expansion
27:40 - Experiments
30:40 - Conclusion

Paper: https://arxiv.org/abs/2401.02415
Other Paper: https://proceedings.mlr.press/v162/shen22f/shen22f.pdf

Abstract:
Humans generally acquire new skills without compromising the old; however, the opposite holds for Large Language Models (LLMs), e.g., from LLaMA to CodeLLaMA. To this end, we propose a new post-pretraining method for LLMs with an expansion of Transformer blocks. …

abstract chinese expansion explained h100 h800 humans introduction language large language llama paper skills