Welcome to RDK S100(P) Board repository
10. MiniCPM-V Visual Multimodal Large Model
MiniCPM-V
MiniCPM-V1. Model Size2. Performance3. Using MiniCPM-V3.1 Running MiniCPM-V3.2 Engaging in a Dialogue3.3 Visual Functions3.4 Ending the Dialogue3.5 Chinese DialogueReferences
Demo Environment
Development Board: RDK S100(P) series motherboard
1. Model Size
| Model | Size |
|---|---|
| minicpm-v:8b | 5.5GB |
2. Performance
3. Using MiniCPM-V
3.1 Running MiniCPM-V
If the system does not have a running model, it will automatically pull the TinyLlama 1.1B model and run it:
xxxxxxxxxxollama run minicpm-v:8b
3.2 Engaging in a Dialogue
xxxxxxxxxxTell me a mathematician story
Response time depends on hardware configuration; please be patient!
3.3 Visual Functions
xxxxxxxxxxWhat do you see in this picture? :./test_pic.png#Using ": + image path" in the dialogue allows the model to use its visual functions to interpret information from the image.
3.4 Ending the Dialogue
Use the shortcut Ctrl+d or /bye to end the dialogue!
3.5 Chinese Dialogue
For those without a Chinese input method, please refer to the Chinese input method switching tutorial.
Chinese Dialogue:
References
Ollama
Official Website: https://ollama.com/
GitHub: https://github.com/ollama/ollama
MiniCPM-V
GitHub: https://github.com/OpenBMB/MiniCPM-o
Ollama Corresponding Model: https://ollama.com/library/minicpm-v