Qwen2

Demonstration environment

Development board: rdk x5 motherboard

sd card: 64G

Tutorial application scope: Whether the motherboard can run is related to the available memory of the system. The user's own environment and the program running in the background may cause the model to fail to run.

Alibaba Qwen2 is an advanced open source large-scale language model developed by Alibaba, designed to provide powerful natural language processing capabilities.

1、Model scale

2、Performance

3. Pull Qwen2

Using the pull command will automatically pull the model from the Ollama model library.

ollama pull qwen2:7b

Small parameter version model.

xxxxxxxxxx
ollama pull qwen2:1.5b

4. Use Qwen2

4.1. Run Qwen2

8gb motherboard runs the following parameters and smaller models:

If the system does not have a running model, the system will automatically pull the Qwen2 7B model and run it:

xxxxxxxxxx
ollama run qwen2:7b

A motherboard with 4 GB of RAM can run this model and smaller models.

xxxxxxxxxx
ollama run qwen2:1.5b

4.2. Have a conversation

xxxxxxxxxx
Please tell me how many hours there are in a day

The response time is related to the hardware configuration, please be patient.

4.3. End the conversation

Use the Ctrl+d shortcut key or /bye to end the conversation!

References

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