-
Notifications
You must be signed in to change notification settings - Fork 48
feat: support fit() in GeminiTextGenerator #758
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
Conversation
tests/system/load/test_llm.py
Outdated
model_name="gemini-pro", max_iterations=1 | ||
) | ||
|
||
df = llm_fine_tune_df_default_index.dropna().sample(n=100) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
don't need to dropna and sample after #760
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks
X, y = utils.convert_to_dataframe(X, y) | ||
|
||
options = self._bqml_options | ||
options["endpoint"] = "gemini-1.0-pro-002" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Spill out the model version to be used for tuning in docs.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Our model name is "gemini-pro-1.0", but their endpoint is called "gemini-1.0-pro-002". Any ideas for how to spill out it?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
synced offline, no need to document the model version now: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versioning#auto-updated-models
GeminiTextGenerator: Fitted estimator. | ||
""" | ||
if self._bqml_model.model_name.startswith("gemini-1.5"): | ||
raise NotImplementedError("Fit is not supported for gemini-1.5 model.") |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Also mention supported model types in docs.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done.
Thank you for opening a Pull Request! Before submitting your PR, there are a few things you can do to make sure it goes smoothly:
Fixes internal #343765747🦕