Describe Your Changes

This PR is to revamp model persistence and its properties:

• Settings & Params are flattened
• No decoration metadata such as description, format, tags, metadata ...
• Some of the properties are updated:
  • sources -> files (string [] or multimodal structure)
  • id -> model
• Models are loaded from a YAML file instead of a SQLite database.
• model_id with colon ":" will be replaced by dash "-"
• Removed hard-coded chat inference parameters.
• Support non streaming response
• Removed the duplicated model pull function that returns a weird model ID with the syntax cortex pull llama3. It would return cortex pull llama3:branch after selection.

Model YAML file generated by a pull command

Fixes Issues

• epic: Cortex supports preset configuration list #617 (1, 2, 3 & 5)
• feat: Cor‌‌tex Storage has File System Support with YAML #616

Self Checklist

• Added relevant comments, esp in complex areas
• Updated docs (for bug fixes / features)
• Created issues for follow-up changes or refactoring needed