Qwen2 model
Qwen2 modelModel scalePerformance performanceGot Qwen2Use Qwen2Run Qwen2DialogueEnd conversationReference material
Demonstration environment
**Development Board * *: Raspberry Pi 5B
SD(TF)card：64G（Above 16G, the larger the capacity, the more models can be experienced）
xxxxxxxxxxRaspberry Pi 5B (8G RAM): Run 8B and below parameter modelsRaspberry Pi 5B (4G RAM): Run 3B and below parameter models
Model scale
| Model | 参数 |
|---|---|
| Qwen2 | 0.5B |
| Qwen2 | 1.5B |
| Qwen2 | 7B |
| Qwen2 | 72B |
xRaspberry Pi 5B (8G RAM): Test Qwen2 model with parameters of 7B and below.Raspberry Pi 5B (4G RAM): Test Qwen2 model with parameters of 1.5B and below.
Performance performance
Got Qwen2
Using the pull command will automatically pull the models from the Ollama model library.
Raspberry Pi 5B（8G RAM）
xxxxxxxxxxollama pull qwen2:7b
Raspberry Pi 5B（4G RAM）
xxxxxxxxxxollama pull qwen2:1.5b
Use Qwen2
Run Qwen2
Raspberry Pi 5B（8G RAM）
If the system does not have a running model, the system will automatically pull the Qwen2 7B model and run it.
xxxxxxxxxxollama run qwen2:7b
Raspberry Pi 5B（4G RAM）
If the system does not have a running model, the system will automatically pull the Qwen2 1.5B model and run it.
xxxxxxxxxxollama run qwen2:1.5b
Dialogue
Raspberry Pi 5B（8G RAM）
xxxxxxxxxxTell me something about large language models.
The response time to the question is related to the hardware configuration, please be patient and wait.
Raspberry Pi 5B（4G RAM）
xxxxxxxxxxTell me something about large language models.
The response time to the question is related to the hardware configuration, please be patient and wait.
End conversation
You can end the conversation by using the shortcut key 'Ctrl+d' or '/bye'.
Raspberry Pi 5B（8G RAM）
Raspberry Pi 5B（4G RAM）
Reference material
Ollama
Website：https://ollama.com/
GitHub：https://github.com/ollama/ollama
Qwen2
GitHub：https://github.com/QwenLM/Qwen2
Ollama model：https://ollama.com/library/qwen2