Added saving/loading of embeds and enabled ANSI text file uploads to vault#23
Open
andresdlp wants to merge 2 commits into
Open
Added saving/loading of embeds and enabled ANSI text file uploads to vault#23andresdlp wants to merge 2 commits into
andresdlp wants to merge 2 commits into
Conversation
Basic code to save and load embeddings to and from a .pt file. Allows users to launch model with embeddings without having to generate them every time.
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Two very basic additions:
The embeding vectors can now be saved and loaded. This was implemented using torch.load() and torch.save(). If the user decides to save tensors, they will need to manually delete them if they want to generate embedings from vault again. This is to minimize required input during normal execution on the console.
Added a try-except statement on the upload file to allow for decoding of ANSI-encoding text files. I don't know of how many use cases this helps with but it is an absolute necessity for Spanish speakers.