Skip to content

Checkpoint #128

Open
Open
@dasbts

Description

@dasbts

Hello,

Is it possible to add a checkpoint to continue running? I'm currently somewhere where Colab Pro is not possible, and I want to continue iterating.

I looked into the files and it seems like the OpenAI CLIP contains:
def load(name: str, device: Union[str, torch.device] = "cuda" if torch.cuda.is_available() else "cpu", jit=True):
"""Load a CLIP model

Parameters
----------
name : str
    A model name listed by `clip.available_models()`, or the path to a model checkpoint containing the state_dict 

If it's possible to make checkpoints, would this be a good place to do so?

Thanks in advance, amazing work on this Github.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions