Skip to content

Mistral 7B

Authors: Jiang et al. Year: 2023 ArXiv/Link: https://arxiv.org/abs/2310.06825

Summary

Efficient 7B parameter model outperforming larger models through architectural improvements and training optimizations.

Key Concepts

  • Efficient architecture
  • Grouped-query attention
  • Sliding window attention
  • Model compression
  • Performance efficiency

Impact

Demonstrated superior efficiency for practical deployment

Category

Open Source Models