CLIP CPU #62
Merged
CLIP CPU #62
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Hi, @shawwn converted the CLIP model weights to load on a cpu (https://github.com/shawwn/CLIP/blob/dev/clip_cpu.py). This works fine for HyperTag as long as the torch device is correctly set everywhere. However, urlretrieve() uses a Python user-agent to fetch the weights for which his server gives a 403 so the inline download fails. I'm not sure about weight hosting in general so I've not modified the UA.
|
Cool work! Hmm not sure how we deal with the downloading / licensing of the converted weights. But I would expect them to be under the same license as OG CLIP models. |
|
Ok, I made following changes:
|
|
Ok looks good to me! Merged. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Hi,
Great project!
@shawwn converted the CLIP model weights to load on a cpu (https://github.com/shawwn/CLIP/blob/dev/clip_cpu.py).
This works fine for HyperTag as long as the torch device is correctly set everywhere.
However, urlretrieve() uses a Python user-agent to fetch the weights for which his server gives a 403 so the inline download fails. I'm not sure about weight hosting or licensing in general so I've not modified the UA.
Hopefully this is helpful.