Welcome to ROSMASTER M1 repository
6. DeepSeek DeepSeek-R1 model
DeepSeek-R1
DeepSeek-R11. Model Size2. Performance3. Using DeepSeek-R13.1 Running DeepSeek-R13.2 Engaging in a Dialogue3.3 Ending the Conversation3.4 Chinese DialogueReferences
Demo Environment
Development Boards: Jetson Orin, RDK X5, Raspberry Pi 5 series motherboard
Note: Due to performance limitations, Jetson Orin Nano 4GB, Raspberry Pi 5 2GB/4GB, and RDK X5 4GB versions require a smaller parameter version to run.
DeepSeek-R1 is an open-source large language model (LLM) designed by DeepSeek for understanding and generating code.
1. Model Size
| Model | Size |
|---|---|
| deepseek-r1:1.5b | 1.1GB |
| deepseek-r1:7b | 4.7GB |
| deepseek-r1:8b | 5.2GB |
2. Performance
3. Using DeepSeek-R1
3.1 Running DeepSeek-R1
Use the run command to start running the R model. If you haven't downloaded this model before, it will automatically pull the model from the Ollam model library:
- ORIN user
ollama run deepseek-r1
- PI5, RDK X5 user
xxxxxxxxxxollama run deepseek-r1:8b
3.2 Engaging in a Dialogue
xxxxxxxxxxHow many minutes are there in a day?
The response time depends on your hardware configuration. Please be patient!
3.3 Ending the Conversation
You can end the conversation using the shortcut Ctrl+d or /bye!
3.4 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
DeepSeek-R1
Ollama's corresponding model: https://ollama.com/library/deepseek-r1