Update with new VertexAIModelGarden output format #14444
Closed
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
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎ 1 Ignored Deployment
|
shikanime
force-pushed
the
pr14444
branch
15 times, most recently
from
aae5a65 to
f131a58
Compare
dosubot
bot
added
size:M
shikanime
force-pushed
the
pr14444
branch
5 times, most recently
from
297083e to
cf42493
Compare
|
Vertex AI Model Garden have some wild changes depending on how you run it, I made few fix for specific ones at https://github.com/shikanime/langchain-vertexai-extended.git |
|
Thanks @shikanime 💯 |
baskaryan
added
the
🔌: google
|
Should be against the https://github.com/langchain-ai/langchain-google repo instead! |
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Outdated suggestions cannot be applied.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.
On December 1st, the Google Cloud Vertex AI Model Garden models runtime received an update in the form of
Prompt:\n\t{prompt}\nOutput:\n\t{prompt}and now streams tokens throughout the second level list.This change will break the current behavior of your applications if adequate fixes are not applied.
We are promoting these changes based on our experiences with LLaMA, Falcon, Mistral, and additional models that are distributed directly by Vertex AI Model Garden.
Probably fixes #13370 #10012