Welcome to RDK X5 Board repository
9.Llava-Vision-Multimodal-Model
Llava
Llava1. Model Scale2. Performance3. Using Llava3.1 Running Llava3.2 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 |
|---|---|
| llava:7b | 4.7GB |
2. Performance
3. Using Llava
3.1 Running Llava
Use the run command to start the model. If you have not downloaded this model before, it will be automatically pulled from the Ollama model library:
ollama run llava:7b
3.2 Having a Conversation
xxxxxxxxxxHow many minutes is half an hour?
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
Llava
Ollama Corresponding Model: https://ollama.com/library/llava