Mixed Use

Mixed use is motivated by compute constraints (train cloud, inference local), privacy constraints (sensitive conversation vs. low-risk conversation), and variety of model behaviors (multiple local models).

• Local models for most tasks, and using larger, cloud-served proprietary models for few high-intelligence tasks. (local_cloud_mixed, 13)
• Training on cloud computer, inferencing on local computer. (local_cloud_training, 3) ^localcloudtraining3
  • related to ^cloudfinetuning8
• Local models for private tasks, cloud models (like ChatGPT, not like Azure) for quick answers. (local_cloud_privacy, 2)
• Using a mix of local models. (local_local_mixed, 2)