- Request Access to Llama Models
2. You may need access in both HuggingFace and Meta Website.
3. Once approved you receive email from both (normall its quick within minutes)
4. Specially with email from meta, you get the link to download.
5. Then just follow, these steps
– https://github.com/meta-llama/llama-models/blob/main/README.md
- !pip install llama-stack
- !llama model list –show-all
- !llama model download –source meta –model-id Llama-2-7b
- !cp -r /root/.llama/checkpoints/Llama-2-7b /content/drive/MyDrive
[This last one if using the commands in google colab to persistently download to a folder]
Links:
In Google colab:
!cp -r /root/.llama/checkpoints/Llama-2-7b /content/drive/MyDrive/