Cortex Pull

This CLI command calls the following API endpoint:

• Download Model

This command displays downloaded models, or displays models available for downloading.

There are 3 ways to download models:

• From Cortex’s Built-in models: cortex pull <model_name>
• HuggingFace repository handle: cortex pull <author/RepoID>
• HuggingFace direct URL: cortex pull <huggingface URL ending with .gguf>

Each of these will display the model quantizations available, to be selected for download.

For more information, please refer to Pulling Models.

The downloaded model file will be stored in the Cortex Data Folder.

Usage

Note

You can use the --verbose flag to display more detailed output of the internal processes. To apply this flag, use the following format: cortex --verbose [subcommand].

MacOs/Linux

cortex pull [options] <model_id>

Windows

cortex.exe pull [options] <model_id>

For example, this returns the following:

cortex pull llama3.2

Downloaded models:
    llama3.2:3b-gguf-q4-km

Available to download:
    1. llama3.2:3b-gguf-q2-k
    2. llama3.2:3b-gguf-q3-kl
    3. llama3.2:3b-gguf-q3-km
    4. llama3.2:3b-gguf-q3-ks
    5. llama3.2:3b-gguf-q4-ks
    6. llama3.2:3b-gguf-q5-km
    7. llama3.2:3b-gguf-q5-ks
    8. llama3.2:3b-gguf-q6-k
    9. llama3.2:3b-gguf-q8-0

Select a model (1-9):

Options

Option	Description	Required	Default value	Example
model_id	The identifier of the model you want to download.	Yes	-	mistral
-h, --help	Display help information for the command.	No	-	-h