# Access locally downloaded Llama Model in Notebook

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Faccess-locally-downloaded-llama-model-in-notebook%2F59683%3E%5C
**Category:** Spaces\
**Created:** [October 24, 2023, 11:39am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Faccess-locally-downloaded-llama-model-in-notebook%2F59683 "2023-10-24T11:39:49Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![mox](https://avatars.discourse-cdn.com/v4/letter/m/f04885/32.png) [@mox](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmox)%5C
**Post date:** [October 24, 2023, 11:39am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Faccess-locally-downloaded-llama-model-in-notebook%2F59683%2F1 "2023-10-24T11:39:49Z")

</div>

Hi,

I just downloaded the LLama2 model from the Meta repository (specifically llama.cpp on Mac). Now I want to use it in a Python script. The quntized model file (ggml-model-q4\_0.bin) s stored now on my Mac. How can I now use the LLama tokenizer and load the model? I am used to acquire the model directely via Huggingface and not locally on my laptop.

I downloaded the Llama-7B-chat model and then used the Llama.cpp  
repository to quantize it. Therefore I have 2 folders LLama and Llama.cpp where the actual model is stored (see Screenshot).

 ![Bildschirmfoto 2023-10-24 um 13.49.02](https://us1.discourse-cdn.com/hellohellohello/original/3X/3/9/398ce1c81642cb71fd06b95f7aa524b83db82789.png)

Thanks in advance!