Welcome to RDK X5 Board repository
10.MiniCPM-V-Vision-Multimodal-Model
MiniCPM-V
MiniCPM-V1. Model Scale2. Performance3. Using MiniCPM-V3.1 Running MiniCPM-V3.2 Having a Conversation3.3 Vision Capabilities3.4 Ending the Conversation3.5 Chinese ConversationReferences
Note: The RDK X5 4GB version cannot run this model due to performance limitations.
1. Model Scale
| 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 and run the TinyLlama 1.1B model:
ollama run minicpm-v:8b
3.2 Having a Conversation
xxxxxxxxxxTell me a mathematician story
The response time depends on the hardware configuration, please be patient!
3.3 Vision Capabilities
xxxxxxxxxxWhat do you see in this picture? :./test_pic.png#In a conversation, use ": + the path to the image" to enable the model's vision capabilities and have it analyze the information in the picture.
3.4 Ending the Conversation
Use the Ctrl+d shortcut or /bye to end the conversation!
3.5 Chinese Conversation
If you don't have a Chinese input method, you can refer to the tutorial on switching Chinese input methods.
Chinese conversation:
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