Skip to main content

Free Public Checkpoints

· 2 min read

Get started building models even faster by using Public Checkpoints.

How It Works​

Public checkpoints are a collection of popular public domain machine learning checkpoint files that are loaded by proxiML. If you are planning to use one of the below checkpoints in your model, be sure to select it in the job form as instructed below instead of provisioning worker storage and downloading it yourself.

caution

If you attach a public checkpoint to your job, you accept the terms and conditions documented in any license, readme, or model card file present in the mounted checkpoint directory or at the associated URL listed below.

Currently, the following models are available to attach to jobs for free:

File-based Checkpoints:

Diffusers Compatible Checkpoints:

If you would like a public checkpoint added, please contact us with a link to the checkpoint and a brief description of what you need it for.

Using the Web Platform​

To select a public checkpoint on the job form, check the public box when adding a new checkpoint. The checkpoint field contents will automatically update to the list of available public checkpoints.

Using the SDK​

To use a public checkpoint, specify the checkpoint as a dictionary with the public property set to True.

job = await proximl.jobs.create(
    ...
    model=dict(
          ...
          checkpoints=[
              dict(id="stable-diffusion-v2-1", public=True),
              "my-checkpoint"
          ],
      )
)