updating fine tuning notebook gemini 2-5 flash #2188
Conversation
There was a problem hiding this comment.
Summary of Changes
Hello @erwinh85, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!
This pull request focuses on updating the supervised fine-tuning notebook for article summarization to align with the latest Gemini 2.5 Flash model. The changes ensure that the notebook's instructions and underlying code correctly reference and utilize the updated model, enhancing the tutorial's accuracy and relevance for users.
Highlights
- Model Version Upgrade: The primary change in this pull request is the upgrade of the fine-tuning notebook to utilize the
Gemini 2.5 Flashmodel, replacing all references and the actual model loaded fromGemini 2.0 Flash. - Documentation Alignment: All textual descriptions, headings, and objectives within the notebook have been updated to reflect the use of
Gemini 2.5 Flash, ensuring consistency between the tutorial's content and the model being used. - Code Base Model Update: The
base_modelvariable, which specifies the model to be loaded for fine-tuning, has been functionally updated from"gemini-2.0-flash-001"to"gemini-2.5-flash". - Placeholder Text Refinement: Minor cosmetic changes were made to the placeholder text for
PROJECT_IDandBUCKET_NAME, converting them from uppercase (e.g.,[YOUR_PROJECT_ID]) to lowercase (e.g.,[your-project-id]).
Using Gemini Code Assist
The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.
Invoking Gemini
You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.
| Feature | Command | Description |
|---|---|---|
| Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
| Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
| Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in issue comments and review comments. |
| Help | /gemini help |
Displays a list of available commands. |
Customization
To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.
Limitations & Feedback
Gemini Code Assist is currently in preview and may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments to provide feedback.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
Footnotes
-
Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩
| @@ -394,7 +394,7 @@ | |||
| }, | |||
| "outputs": [], | |||
| "source": [ | |||
| "PROJECT_ID = \"[YOUR_PROJECT_ID]\" # @param {type:\"string\"}\n", | |||
| "PROJECT_ID = \"[your-project-id]\" # @param {type:\"string\"}\n", | |||
There was a problem hiding this comment.
Consider using lowercase for the project ID placeholder for consistency with the bucket name placeholder below.
PROJECT_ID = "[your-project-id]" # @param {type:"string"}
| @@ -485,7 +485,7 @@ | |||
| "outputs": [], | |||
| "source": [ | |||
| "# Provide a bucket name\n", | |||
| "BUCKET_NAME = \"[YOUR_BUCKET_NAME]\" # @param {type:\"string\"}\n", | |||
| "BUCKET_NAME = \"[your-bucket-name]\" # @param {type:\"string\"}\n", | |||
There was a problem hiding this comment.
Consider using lowercase for the bucket name placeholder for consistency with the project ID placeholder above.
BUCKET_NAME = "[your-bucket-name]" # @param {type:"string"}
| @@ -1151,7 +1151,7 @@ | |||
| " - `tuned_model_display_name`: Display name for the tuned model.\n", | |||
| " - `epochs`: The number of training epochs to run.\n", | |||
| " - `learning_rate_multiplier`: A value to scale the learning rate during training.\n", | |||
| " - `adapter_size` : Gemini 2.0 Pro supports Adapter length [1, 2, 4, 8], default value is 4." | |||
| " - `adapter_size` : Gemini 2.5 Flash supports Adapter length [1, 2, 4, 8], default value is 4." | |||
There was a problem hiding this comment.
The description states that Gemini 2.0 Pro supports the adapter size, but this notebook is for Gemini 2.5 Flash. Update the description to reflect the correct model.
- `adapter_size` : Gemini 2.5 Flash supports Adapter length [1, 2, 4, 8], default value is 4.
|
Minor code change |
Description
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:
CONTRIBUTINGGuide.CODEOWNERSfor the file(s).nox -s formatfrom the repository root to format).Fixes #<issue_number_goes_here> 🦕