knowledgebase/pages/Experimenting with LLM.md

Hardware and OS

- ThinkCentre m700q
	- Output from `neofetch`
	- ![image.png](../assets/image_1708187142637_0.png)

• Install ollama

  • To install ollama follow the instruction on GitHub

    • curl -fsSL https://ollama.com/install.sh | sh
      

• Download and run a model

  • Execute ollama run <modelname>

    • ollama run phi
      

  • Dowload a custom model from HugginFace

    • wget https://huggingface.co/DeepMount00/Mistral-Ita-7b-GGUF/resolve/main/mistal-Ita-7b-q4_k_m.gguf