-
Notifications
You must be signed in to change notification settings - Fork 348
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.
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
chore(main): release 1.31.1 #2507
Merged
sasha-gitg
merged 2 commits into
googleapis:release-v1.31.1
from
sasha-gitg:release-v1.31.1
Aug 25, 2023
Merged
chore(main): release 1.31.1 #2507
sasha-gitg
merged 2 commits into
googleapis:release-v1.31.1
from
sasha-gitg:release-v1.31.1
Aug 25, 2023
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
… `CodeGenerationModel` The previously default value (128) was inconsistent with the service-side default values of the models: `code-bison` has 1024 and `code-gecko` has 64. More so, the default value was out of range of the `code-gecko` model. This CL fixes these issues. The SDK now relies on the service-side default values when the user does not pass a parameter value explicitly. What can change: When using the `code-bison` model, the default value of `max_output_tokens` effectively increases from 128 to 1024 (the current service-side default value). PiperOrigin-RevId: 559266968
product-auto-label
bot
added
size: m
Pull request size is medium.
api: vertex-ai
Issues related to the googleapis/python-aiplatform API.
labels
Aug 24, 2023
yinghsienwu
approved these changes
Aug 25, 2023
sasha-gitg
added a commit
to sasha-gitg/python-aiplatform
that referenced
this pull request
Aug 25, 2023
* fix: LLM - De-hardcoded the `max_output_tokens` default value for the `CodeGenerationModel` The previously default value (128) was inconsistent with the service-side default values of the models: `code-bison` has 1024 and `code-gecko` has 64. More so, the default value was out of range of the `code-gecko` model. This CL fixes these issues. The SDK now relies on the service-side default values when the user does not pass a parameter value explicitly. What can change: When using the `code-bison` model, the default value of `max_output_tokens` effectively increases from 128 to 1024 (the current service-side default value). PiperOrigin-RevId: 559266968 * chore(main): release 1.31.1 --------- Co-authored-by: Alexey Volkov <[email protected]>
copybara-service bot
pushed a commit
that referenced
this pull request
Aug 25, 2023
-- 73439c6 by release-please[bot] <55107282+release-please[bot]@users.noreply.github.com>: chore(main): release 1.31.0 (#2450) Co-authored-by: release-please[bot] <55107282+release-please[bot]@users.noreply.github.com> -- 3d468ed by sasha-gitg <[email protected]>: chore(main): release 1.31.1 (#2507) * fix: LLM - De-hardcoded the `max_output_tokens` default value for the `CodeGenerationModel` The previously default value (128) was inconsistent with the service-side default values of the models: `code-bison` has 1024 and `code-gecko` has 64. More so, the default value was out of range of the `code-gecko` model. This CL fixes these issues. The SDK now relies on the service-side default values when the user does not pass a parameter value explicitly. What can change: When using the `code-bison` model, the default value of `max_output_tokens` effectively increases from 128 to 1024 (the current service-side default value). PiperOrigin-RevId: 559266968 * chore(main): release 1.31.1 --------- Co-authored-by: Alexey Volkov <[email protected]> COPYBARA_INTEGRATE_REVIEW=#2509 from googleapis:release-v1.31.1 3d468ed PiperOrigin-RevId: 560187793
pabloem
pushed a commit
to pabloem/python-aiplatform
that referenced
this pull request
Dec 30, 2023
-- 73439c6 by release-please[bot] <55107282+release-please[bot]@users.noreply.github.com>: chore(main): release 1.31.0 (googleapis#2450) Co-authored-by: release-please[bot] <55107282+release-please[bot]@users.noreply.github.com> -- 3d468ed by sasha-gitg <[email protected]>: chore(main): release 1.31.1 (googleapis#2507) * fix: LLM - De-hardcoded the `max_output_tokens` default value for the `CodeGenerationModel` The previously default value (128) was inconsistent with the service-side default values of the models: `code-bison` has 1024 and `code-gecko` has 64. More so, the default value was out of range of the `code-gecko` model. This CL fixes these issues. The SDK now relies on the service-side default values when the user does not pass a parameter value explicitly. What can change: When using the `code-bison` model, the default value of `max_output_tokens` effectively increases from 128 to 1024 (the current service-side default value). PiperOrigin-RevId: 559266968 * chore(main): release 1.31.1 --------- Co-authored-by: Alexey Volkov <[email protected]> COPYBARA_INTEGRATE_REVIEW=googleapis#2509 from googleapis:release-v1.31.1 3d468ed PiperOrigin-RevId: 560187793
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Labels
api: vertex-ai
Issues related to the googleapis/python-aiplatform API.
size: m
Pull request size is medium.
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.
No description provided.