Example Notebooks
E-Commerce Embedding Model Comparison(View in Google Colab)This shows how to apply Cobalt’s model comparison table to choose the best embedding model for your e-commerce vector database. Cobalt intelligently clusters together users’ product search queries into valuable and interpretable categories on which to compare different models.
E-Commerce Embedding Model Comparison (Fine-Tuning)(View in Google Colab)Similar to the above, but focused on tradeoffs from fine-tuning. The two models are a base E5 model from Hugging Face, and its fine-tuned version from using Marqo’s Marqtune platform to fine-tune. Cobalt reveals performance tradeoffs from fine-tuning through the model comparison table. Read more about our Marqtune integration here.
-
This is a simple example using a synthetic tabular dataset and
scikit-learn-based model to illustrate the main parts of the Cobalt interface. The same example is outlined in the Tutorial. -
Uses Cobalt to explore and debug a transformer-based text classification model from Hugging Face. Requires the
transformerspackage to be installed. -
A simple illustration of how Cobalt can help diagnose and understand data drift even in the absence of a model or model performance metrics.
-
This is an example that demonstrates the use of Cobalt to make sense of the ImageNette dataset, and explore its target labels, by making use of embeddings generated by the CLIP model.
This notebook requires the OpenAI
clippackage to be installed, which includestorch,torchvision, etc…