🤖 EmbeddingGemma Tuning Lab: Fine-Tuning and Mood Reader

This project provides a set of tools to fine-tune EmbeddingGemma to understand your personal taste in Hacker News titles and then use it to score and rank new articles based on their "vibe". The core idea is to measure the "vibe" of a news title by calculating the semantic similarity between its embedding and the embedding of a fixed anchor phrase, MY_FAVORITE_NEWS.
See README for more details.
Base Model for Fine-tuning

Sign in to Hugging Face if you plan to push your fine-tuned model to the Hub later (Step 3).

Select titles from the live Hacker News feed OR upload your own CSV dataset to prepare your training data.

Rate the stories below to define your vibe.

⚠️ Note: You must select at least one Favorite and one Dislike to run training.

Upload a CSV file with columns (no header required, or header ignored if present): Anchor, Positive, Negative.

See also: example_training.dataset.csv
Example:
MY_FAVORITE_NEWS,Good Title,Bad Title

Fine-tune the model using the data selected or uploaded above.

Push your fine-tuned model to your personal Hugging Face account.

Target Repository: (Waiting for input...)

Export your combined dataset or download the fine-tuned model locally.

Ready.