Avoid duplicating PyTorch + safetensors downloads. #1836
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Duplication happens when there are safetensors versions of some files in the repo but not all.
Ideally, we should just download safetensors files when they are available, and fallback to PyTorch when they are not. This could be done by retrieving the list of files in the repo using
list_repo_files
(ormodel_info
) and filtering them to keep the ones we want. A similar mechanism could be applied to downloadfp16
versions when they exist.Addresses #1811.