docs: add demo .webm, platform disclaimer, MCP link, and finetune example#44
Merged
Merged
Conversation
sethtroisi
approved these changes
Jun 4, 2026
…mple - README: embed CLI demo (docs/demo.webm, 929 KB VP9 WebM) at the top via HTML5 <video> tag with a raw URL pointing at main - README: add Linux/macOS-only platform support disclaimer - README: add pointer to googlecolab/colab-mcp for in-notebook agent workflows - examples/finetune_run.py: new QLoRA fine-tuning example for Gemma 3 1B on a T4 via 'colab exec -f', demonstrating end-to-end script execution
f58b3a5 to
3521ea6
Compare
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Updates the README with three additions and creates a new
examples/directory containing a Gemma 3 1B QLoRA fine-tuning script.README changes
docs/demo.webm, ~1 MB)> [!NOTE]callout stating that the CLI currently supports Linux and macOS only (Windows is not supported at this time).> [!TIP]callout pointing users who want in-notebook, interactive agent-assisted coding to the Colab MCP Server.New example
examples/finetune_run.py: A new fine-tuning example that runs Gemma 3 1B with QLoRA on thephilschmid/gretel-synthetic-text-to-sqldataset. Demonstrates the end-to-endcolab exec -fflow on a T4 (4-bit quant, LoRA adapter, ~60 steps for demo timing). Includes header comments documenting theHF_TOKENsetup workflow.Review