Gemma model

Gemma modelModel scaleGot GemmaRun GemmaRun GemmaDialogueEnd conversationReference material

Demonstration environment

Development board : Raspberry Pi 5B (8G RAM)

SD(TF)card:64G(Above 16G, the larger the capacity, the more models can be experienced)

Gemma is a new open model developed by Google and its DeepMind team.

Model scale

ModelParameter
Gemma2B
Gemma7B

Got Gemma

Using the pull command will automatically retrieve the models from the Ollama model library.

Raspberry Pi 5B(8G RAM)

image-20240625155422676

Raspberry Pi 5B(4G RAM)

image-20240626170059107

Run Gemma

Run Gemma

Raspberry Pi 5B(8G RAM)

If the system does not have a running model, the system will automatically pull the Gemma 7B model and run it:The factory image does not provide this image, you need to download it yourself!

Raspberry Pi 5B(4G RAM)

If the system does not have a running model, the system will automatically obtain the Gemma 2B model and run it.

Dialogue

Raspberry Pi 5B(8G RAM)

The time to reply to the question is related to the hardware configuration, please be patient.

image-20240625160236635

Raspberry Pi 5B(4G RAM)

The time to reply to the question is related to the hardware configuration, please be patient.

image-20240626170852576

End conversation

You can end the conversation by using the shortcut key 'Ctrl+d' or '/bye'.

Raspberry Pi 5B(8G RAM)

image-20240625160455267

Raspberry Pi 5B(4G RAM)

image-20240626171040189

Reference material

Ollama

Website:https://ollama.com/

GitHub:https://github.com/ollama/ollama

Gemma

GitHub:https://github.com/google-deepmind/gemma

Ollama model:https://ollama.com/library/gemma