GitBross Inicio Explorar Ayuda
Registro Iniciar sesión
sol_87yf6cwp
/
LLMs-from-scratch
espejo de https://github.com/br8bit/LLMs-from-scratch.git
1
0
Fork 0
Archivos Incidencias 0 Wiki
Rama: main
Ramas Etiquetas
LLMs-from-scrat...
/
ch05
/
12_gemma3
Sebastian Raschka 80d4732456 add HF equivalency tests for standalone nbs (#774) hace 3 meses
..
tests 80d4732456 add HF equivalency tests for standalone nbs (#774) hace 3 meses
README.md a6b883c9f9 Gemma 3 270M From Scratch (#771) hace 3 meses
standalone-gemma3.ipynb a6b883c9f9 Gemma 3 270M From Scratch (#771) hace 3 meses

README.md

Gemma 3 270M From Scratch

This standalone-gemma3.ipynb Jupyter notebook in this folder contains a from-scratch implementation of Gemma 3 270M. It requires about 2 GB of RAM to run.

Below is a side-by-side comparison with Qwen3 0.6B as a reference model; if you are interested in the Qwen3 0.6B standalone notebook, you can find it here.



To learn more about the architecture differences and read about comparisons with other architectures, see my The Big LLM Architecture Comparison: From DeepSeek-V3 to Kimi K2: A Look At Modern LLM Architecture Designarticle.