Skip to content

Conversation

@jayesh-tanna
Copy link
Member

Description

Please add an informative description that covers that changes made by the pull request and link all relevant issues.

If an SDK is being regenerated based on a new API spec, a link to the pull request containing these API spec changes should be included above.

All SDK Contribution checklist:

  • The pull request does not introduce [breaking changes]
  • CHANGELOG is updated for new features, bug fixes or other significant changes.
  • I have read the contribution guidelines.

General Guidelines and Best Practices

  • Title of the pull request is clear and informative.
  • There are a small number of commits, each of which have an informative message. This means that previously merged commits do not appear in the history of the PR. For more information on cleaning up the commits in your PR, see this page.

Testing Guidelines

  • Pull request includes test coverage for the included changes.

@github-actions
Copy link

github-actions bot commented Nov 3, 2025

API Change Check

APIView identified API level changes in this PR and created the following API reviews

azure-ai-projects


Before running the sample:

pip install azure-ai-projects azure-identity openai python-dotenv
Copy link
Member

Choose a reason for hiding this comment

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

Please use this in the pip install command (all samples): "azure-ai-projects>=2.0.0b1"

Supported OSS models with SFT technique: Ministral-3b , Llama-3.3-70b , Qwen3-32b , Gpt-oss-20b

USAGE:
python sample_finetuning_supervised_job.py
Copy link
Member

Choose a reason for hiding this comment

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

Update sample name to match actual file name. Please check other samples as well. Thanks!

"""
DESCRIPTION:
Given an AIProjectClient, this sample demonstrates how to use the synchronous
`.fine_tuning.jobs` methods to create supervised fine-tuning jobs using OSS model.
Copy link
Member

Choose a reason for hiding this comment

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

Can you expand OSS? write "Open Source Software (OSS)"... if I got it correct.

`.fine_tuning.jobs` methods to create, get, list, cancel, pause, resume, list events and list checkpoints supervised fine-tuning jobs.
It also shows how to deploy the fine-tuned model using Azure Cognitive Services Management Client and perform inference on the deployed model.
Supported OAI Models: GPT 4o, 4o-mini, 4.1, 4.1-mini

Copy link
Member

Choose a reason for hiding this comment

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

Perhaps shorter lines above (break up long line into two). Same in other samples.

2) MODEL_NAME - Optional. The base model name to use for fine-tuning. Default to the `gpt-4o` model.
3) TRAINING_FILE_PATH - Optional. Path to the training data file. Default to the `data` folder.
4) VALIDATION_FILE_PATH - Optional. Path to the validation data file. Default to the `data` folder.
"""
Copy link
Member

Choose a reason for hiding this comment

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

Can you please update .env.template with placeholders for these env variables? (and a comment line mentioning that these are used by Fine Tuning samples)

@dargilco
Copy link
Member

dargilco commented Nov 6, 2025

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants