Skip to content
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

Add Text-Generation/Chat MaaP FineTuning sample #3459

Open
wants to merge 7 commits into
base: main
Choose a base branch
from

Conversation

sagarsumant
Copy link
Member

Description

Checklist

  • I have read the contribution guidelines.
  • I have coordinated with the docs team (mldocs@microsoft.com) if this PR deletes files or changes any file names or file extensions.
  • Pull request includes test coverage for the included changes.
  • This notebook or file is added to the CODEOWNERS file, pointing to the author or the author's team.

@sagarsumant sagarsumant changed the title Add Text-Generation MaaP FineTuning sample Add Text-Generation/Chat MaaP FineTuning sample Dec 10, 2024
"source": [
"## FineTuning LLM with Model-As-Service\n",
"\n",
"This sample shows how use create a standalone FineTuning job to fine tune a model to summarize a dialog between 2 people using samsum dataset.\n",

Choose a reason for hiding this comment

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

typo in " how use create"

"source": [
"## FineTuning LLM with Model-As-Service\n",
"\n",
"This sample shows how use create a standalone FineTuning job to fine tune a model to summarize a dialog between 2 people using samsum dataset.\n",

Choose a reason for hiding this comment

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

What's the meaning of 'standalone' - what are the other options ?

"cell_type": "markdown",
"metadata": {},
"source": [
"### 2. Pick a foundation model to fine tune\n",

Choose a reason for hiding this comment

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

There is no reference to 'foundational' in UI. What's the reason to use the term here ?

"outputs": [],
"source": [
"model_name = \"Phi-3-mini-4k-instruct\"\n",
"foundation_model = registry_ml_client.models.get(model_name, label=\"latest\")\n",

Choose a reason for hiding this comment

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

how about just 'model' instead of 'foundation_model' ?

"outputs": [],
"source": [
"model_name = \"Phi-3-mini-4k-instruct\"\n",
"foundation_model = registry_ml_client.models.get(model_name, label=\"latest\")\n",

Choose a reason for hiding this comment

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

Do we have to expose a version as part of the sample? User cannot select a version in AIStudio

"cell_type": "markdown",
"metadata": {},
"source": [
"## FineTuning LLM with Model-As-Service\n",

Choose a reason for hiding this comment

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

Wrong title ? Is this about MaaS or MaaP ?

To run the fine-tuning job, use the following command:

```bash
az ml job create --file text-generation-finetuning-amlcompute.yaml --resource-group hyperdrive-service-static-rg --workspace-name train-finetune-dev-eastus --name "ft-maap-llama3-instance-types-1209-01"
Copy link
Contributor

Choose a reason for hiding this comment

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

consider using instead of hardcoded values for rg, ws etc.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants