LLaVA

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）

Raspberry Pi 5B (16G RAM): Run 14B and below parameter models
Raspberry Pi 5B (8G RAM): Run 8B and below parameter models
Raspberry Pi 5B (4G RAM): Run 3B and below parameter models， can't run LLaVA
Raspberry Pi 5B (2G RAM): Run 0.5B and below parameter models， can't run LLaVA

LLaVA (Large scale Language and Vision Assistant) is a multimodal model aimed at achieving universal visual and language understanding by combining visual encoders and large-scale language models.

Model scale

xxxxxxxxxx
Raspberry Pi 5B (8G RAM): LLaVA model testing with 7B parameters.

Got LLaVA

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

xxxxxxxxxx
ollama pull llava:7b

Use LLaVA

Use LLaVA to recognize local image content.

Run LLaVA

If the system does not have a running model, the system will automatically pull the LLaVA 7B model and run it.

xxxxxxxxxx
ollama run llava:7b

Dialogue

xxxxxxxxxx
What's in this image? /home/pi/1.jpeg

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

End conversation

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

Reference material

Ollama

Website：https://ollama.com/

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

LLaVA

GitHub：https://github.com/haotian-liu/LLaVA

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