Ornith-1.0-9B and Ornith-1.0-3... Note

Ornith-1.0-9B and Ornith-1.0-35B models now available on Amazon SageMaker JumpStart

DeepReinforce AI's Ornith-1.0-9B and Ornith-1.0-35B models are now available on Amazon SageMaker JumpStart. These open-source, self-scaffolding agentic coding models achieve state-of-the-art performance on various coding benchmarks. Ornith-1.0-9B is a lightweight 9B-parameter model, optimized for single-GPU deployment and ideal for individual developers. It features a 256K-token context window and uses reinforcement learning to improve code solutions. Ornith-1.0-35B is a 35B-parameter Mixture-of-Experts (MoE) model, offering stronger performance while still deployable on a single consumer GPU. This larger model also utilizes reinforcement learning to optimize code trajectories and solution rollouts. Its MoE architecture balances quality and efficiency for production coding. Both models are released under the MIT license, expanding the foundation models available to AWS customers. SageMaker JumpStart enables easy deployment of these models for specific AI use cases with just a few clicks. Users can access these models through the SageMaker console or the SageMaker Python SDK. More information is available in the Amazon SageMaker JumpStart documentation.