Orca 2 models are trained using a teacher-student scheme, where a larger, more powerful LLM acts as a teacher for a smaller student LLM, with the goal of improving the performance of the student to be comparable with that of a larger model.
When evaluated on benchmarks, a 13B parameter Orca 2 model outperformed a baseline 13B parameter Llama 2 by 47.54%.

Key Features of our AMI:
Instant Deployment: In contrast to the extensive raw model, the AMI version enables quick launches, removing the need for complex setup procedures.

API Connectivity: Equipped with a strong API, it guarantees smooth interaction with various applications, enhancing adaptability.

Compatibility with OpenAI: Specifically designed for OpenAI-aligned projects, this AMI ensures compatibility and effortless integration within the OpenAI ecosystem.