This repository was archived by the owner on Jan 15, 2026. It is now read-only.
fix: pull onnx models from huggingface instead of GCS (WIP)#36
Draft
nleroy917 wants to merge 7 commits into
Draft
fix: pull onnx models from huggingface instead of GCS (WIP)#36nleroy917 wants to merge 7 commits into
nleroy917 wants to merge 7 commits into
Conversation
nleroy917
changed the title
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 subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This prioritizes huggingface weights over ones stored in google cloud storage (GCS). The reason is twofold: 1) the python
fastembedimplementation does this, and 2) we shouldnt point at GCS. When people are usingsentence-transformersandfastembedthey expect embeddings to be the same... we have zero control over what weights they are putting onall-MiniLM-L6-v2orbge-small-en-v1.5, and so we should point to them as a source of truth.This addresses some issues in: #30
However, some of the models this module supports (
bge-small-zh,bge-small-en) dont actually have onnx weights on HF so that can be a problem.