Downloading Phi 2.0
Last updated
This documentation is for the Axolotl community
Last updated
The screen cut below is from the Huggingface Models Database - specifically Phi 2.0.
To download the model, left click on the vertical three dots next to the "TRAIN" button.
You can click on the diagram below to see the three vertical dots:
When you left click the three vertical docks you can see the instructions to download the model to your local host.
Enter the command below at your prompt:
If you don't want to download the entire model files due to bandwidth issues, you can set the environmental variable as per below prior to downloading the model using the git clone command,.
Setting GIT_LFS_SKIP_SMUDGE=1
tells Git LFS to skip the automatic downloading of the actual content of large files tracked by LFS when cloning a repository.
Instead, only the pointer files are cloned.
The "smudge" process is what usually replaces these pointers with the actual file content during cloning.
By skipping this, you speed up the cloning process and save bandwidth, especially useful if you don't need the large files immediately or are only interested in the repository's code or smaller files.
By running this command, you clone the microsoft/phi-2
repository without immediately downloading the large files tracked by LFS. If you later decide that you need these large files, you can use Git LFS commands to fetch them.
If you download all the files using the git clone command you should see the following folder and associated files in your VS Code IDE:
With the model downloaded to your local directory, the next step is to download the dataset you wish to use for fine tuning the model.