Small Language Models: Using 3.8b Phi 3 and 8b Llama 3 Models on a Pc and Raspberry Pi


Testing the models with LlamaCpp and ONNX
Towards Data Science 12:53 pm on May 23, 2024


Testing small language models like Phi-3 and Llama-3 with PCs and Raspberry Pi by Dmitrii Eliuseev shows feasibility in limited resources. The text discusses deploying these models using LlamaCpp, ONNX for cross-platform compatibility, and the implications on data science practices.

  • Model Selection: Phi-3 & Llama-3 are chosen due to their balance between performance and resource demands.
  • Testing Platforms: Models are tested on PCs and Raspberry Pi, showcasing versatility across devices.
  • LlamaCpp and ONNX: Utilization of LlamaCpp for model execution and ONNX format for cross-platform compatibility.
  • Implications: Highlights the trend toward more accessible AI development without full reliance on high-powered hardware.
  • Authorship and Publication: By Dmitrii Eliuseev, published in 'Towards Data Science' reflecting current industry insights.
Category
https://towardsdatascience.com/small-language-models-using-3-8b-phi-3-and-8b-llama-3-models-on-a-pc-and-raspberry-pi-9ed70127fe61

< Previous Story     -     Next Story >

Copy and Copyright Pubcon Inc.
1996-2024 all rights reserved. Privacy Policy.
All trademarks and copyrights held by respective owners.