This repository has been archived by the owner on Oct 25, 2024. It is now read-only.
A beginner friendly quantize and text embeddings tutorial for XPUs #1663
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
in this notebook, I have showed how text embeddings can be generated using HF models and quantise them at the same moment on Intel XPUs Signed-off-by: tawsif <[email protected]>
Signed-off-by: tawsif <[email protected]>
|
@sleepingcat4 Looks good! Could you please provide some screenshots of jupyter notebook results in this PR? |
|
@Zhenzhong1 sure!
|
|
Here's another screenshot (although this is from another script where I distributed 8 files on 8 Intel XPUs)
|
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
I have added a beginner friendly tutorial to illustrate how HF text embedding models can be quantised and loaded using Intel XPUs and then use to generate embeddings. (through jupyter notebook)
I have used "BAAI/bge-m3" model from HF and used Intel extension for transformers and transformers library to quantise it on XPU.