Meta AI Codellama model
Meta AI Codellama modelModel scaleGot Code LlamaUse Code LlamaRun Code LlamaDialogueReference material
Demonstration environment
Development Board : Raspberry Pi 5B
SD(TF)card：64G（Above 16G, the larger the capacity, the more models can be experienced）
xRaspberry Pi 5B (16G RAM): Run 14B and below parameter modelsRaspberry Pi 5B (8G RAM): Run 8B and below parameter modelsRaspberry Pi 5B (4G RAM): Run 3B and below parameter modelsRaspberry Pi 5B (2G RAM): Run 0.5B and below parameter models, can't run Codellama model
Code Llama is an open-source Large Language Model (LLM) specifically designed by the Meta AI department for understanding and generating code.
Model scale
| Model | Parameter |
|---|---|
| Code Llama | 7B |
| Code Llama | 13B |
| Code Llama | 34B |
| Code Llama | 70B |
xxxxxxxxxxRaspberry Pi 5B (8G RAM): Code Llama model testing using 7B parameters
Got Code Llama
Using the pull command will automatically pull the models from the Ollama model library.
xxxxxxxxxxollama pull codellama:7b
Use Code Llama
Run Code Llama
If the system does not have a running model, the system will automatically pull the Code Llama 7B model and run it.
xxxxxxxxxxollama run codellama:7b
Dialogue
xxxxxxxxxxWrite me a function that outputs the fibonacci sequence
The time to reply to the question is related to the hardware configuration, please be patient.
End conversation
You can end the conversation by using the shortcut key 'Ctrl+d' or '/bye'.
Reference material
Ollama
Website：https://ollama.com/
GitHub：https://github.com/ollama/ollama
Code Llama
Ollama Model：https://ollama.com/library/codellama