Nexa AI

3 updates on Nexa AI.

  1. Octopus v3 picks an action from an image and a query in under 1B parameters

    A technical report describes a sub-billion multimodal agent that turns an image and a text query into a function call, shown through ten worked examples.

  2. Octopus v2 is a 2B model that calls Android APIs with one token per function

    A 2B Gemma fine-tune gives every Android API its own token, and the authors report 99.524% accuracy and 0.38 seconds per call, ahead of GPT-4.

  3. Octopus fine-tunes a 2B model to 93 percent on API function calls

    Stanford and Harvard authors fine-tuned open 2B to 7B models on 20,000 RapidAPI functions and report up to 97 percent function call accuracy.