Skip to main content

Release Notes


September 20, 2021 - New & Improved Generation and Embedding Models otter (representation) is now our best representation model to date, and internal tests show a stark improvement in a wide class of downstream tasks. We recommend migrating all upcoming embedding usage.

shark (generation) has significant advancements in speed and performance and now has double the capacity of tokens (2048). Any new calls to baseline-shark will be served by this new model.

August 9, 2021 - Seal Model Update

The updated seal model runs faster with a noticeable increase in quality, shown by our internal tests. This model is generally more performant across all tasks, especially those involving common sense, reasoning, and reading comprehension.

This update is automatic. Any code pointed towards the seal model will start seeing these improvements immediately.

July 21, 2021 - Choose Best Likelihoods

The Choose Best endpoint now returns scores, tokens, and token_log_likelihoods.

July 13, 2021 - Finetuning Validation

Sample validation is now available in the dashboard. Upon uploading a .txt file, there is an option to "Review your Finetine" to validate a set of sample training data.