Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Transformers example #3743

Merged
merged 5 commits into from
Nov 17, 2021
Merged

Transformers example #3743

merged 5 commits into from
Nov 17, 2021

Conversation

adriangonz
Copy link
Contributor

What this PR does / why we need it:

Add example on how to build a custom pre-processor / transformer compatible with the V2 inference protocol, to then deploy it alongside a GPT-2 model in a SeldonDeployment inference graph.

Which issue(s) this PR fixes:

Fixes #3732

Special notes for your reviewer:

Does this PR introduce a user-facing change?:

NONE

@review-notebook-app
Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.

Powered by ReviewNB

@adriangonz adriangonz requested a review from axsaucedo November 16, 2021 17:29
@seldondev seldondev added size/L and removed size/XL labels Nov 16, 2021
@ukclivecox
Copy link
Contributor

looks great @adriangonz

@axsaucedo
Copy link
Contributor

Looks good! Seems image doesn't render when opening the notebook in github but assuming it would work in notebook (as is svg)

It seems the docs test is failing (normally the build has been failing but the lint is passsing so wondering if its anything related)

edshee
edshee approved these changes Nov 17, 2021
View reviewed changes
Copy link
Contributor

@edshee edshee left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Adrian this is great. Well written and explains the components you're using at each step 👏

@seldondev
Copy link
Collaborator

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: edshee
To complete the pull request process, please assign adriangonz
You can assign the PR to them by writing /assign @adriangonz in a comment when ready.

The full list of commands accepted by this bot can be found here.

Needs approval from an approver in each of these files:

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

@edshee
Copy link
Contributor

edshee commented Nov 17, 2021

/assign adriangonz

@ukclivecox ukclivecox merged commit a1aff8e into SeldonIO:master Nov 17, 2021
stephen37 pushed a commit to stephen37/seldon-core that referenced this pull request Dec 21, 2021
Transformers example (SeldonIO#3743)
918665f 
* Add tokeniser example

* Link notebook on examples page

* Make NOTE bold and remove outputs

* Change references to other notebook to links to docs

* Change MLServer version explicitly to 0.6.0.dev3
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@edshee edshee edshee approved these changes

@axsaucedo axsaucedo Awaiting requested review from axsaucedo

@ukclivecox ukclivecox Awaiting requested review from ukclivecox

Assignees

@adriangonz adriangonz

Labels
size/L
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Add model chaining example for the V2 protocol
5 participants
@adriangonz @ukclivecox @axsaucedo @seldondev @edshee