Welcome to ROSMASTER R2 repository
7.DeepSeek-R1 model
DeepSeek-r1
DeepSeek-r1Model scaleUpdate Ollama versionUsing DeepSeek-r1Run DeepSeek-r1Have a conversationEnd the conversationReferences
Demo Environment
Development Boards：Jetson Nano
SD (TF) card/U disk：64G
It is recommended to run the 4B and below parameter models
DeepSeek-r1 is an open source Large Language Model (LLM) designed by DeepSeek for understanding and generating code.
Model scale
| Model | Parameter |
|---|---|
| DeepSeek-r1 | 1.5B |
| DeepSeek-r1 | 7B |
| DeepSeek-r1 | 8B |
| DeepSeek-r1 | 14B |
xxxxxxxxxxJetson Nano: Can only use DeepSeek-r1 model with 1.5B parameters!
Update Ollama version
Using the installation command will automatically update the ollama version, which takes a long time. It depends on your network:
xxxxxxxxxxcurl -fsSL https://ollama.com/install.sh | sh
It will show that the installation is complete. When checking the version of ollam, it will show a correct version, and the version greater than 0.1.48 will be updated.
Using DeepSeek-r1
Run DeepSeek-r1
When using the large language model image provided by Yabo Intelligence, please note that the DeepSeek-R1 model is not pre-installed in the image. You can automatically download and install the DeepSeek-R1 model by running the following command. After running the command, the system will automatically enter the dialogue interface:
xxxxxxxxxxollama run deepseek-r1:1.5b
Wait for the automatic pull to complete, and then enter the dialogue interface automatically.
Have a conversation
Let the model introduce itself：
xxxxxxxxxxwho are you？
Consult other issues：
xxxxxxxxxxHow many centimeters equal one meter?
The response time is related to the hardware configuration, please be patient.
End the conversation
Use the Ctrl+d shortcut or /bye to end the conversation!
References
Ollama
Website：https://ollama.com/
GitHub：https://github.com/ollama/ollama
DeepSeek-R1
Ollama corresponding model：https://ollama.com/library/deepseek-r1
GitHub：https://github.com/deepseek-ai/DeepSeek-r1