Keyboard shortcuts

Press or to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

Model Inventory

Quick Reference

Model NameTypeSizePurposeLocation
Image ModelsVarious149GBImage generation, visionmodels/image-models/
Text ModelsLLMs122GBText generation, NLPmodels/text-models/
Local Learning120BTBD24/7 learning systemtraining/local-learning-system/

Image Models (149GB)

Source: ComfyUI installation Location: models/image-models//home/adminator/comfy/ComfyUI/image-models

Used by:

  • Vision agents
  • Image generation agents
  • Image analysis agents

Note: Symlinked to avoid duplication. Do NOT delete source!

Text Models (122GB)

Source: Llama.cpp installation Location: models/text-models//home/adminator/llama.cpp/text-models

Used by:

  • NLP agents
  • Text generation agents
  • Sentiment analyzers
  • Intent classifiers

Note: Symlinked to avoid duplication. Do NOT delete source!

Local Learning System

Location: training/local-learning-system/

From expert_agents/LOCAL_MODEL_AGENT.md:

  • 24/7 learning capability
  • Knowledge accumulation
  • Offline inference
  • Custom domain learning

Integration: Connect this to SMO for continuous learning

Specialized Systems

Vision System

Computer vision components and pipelines.

Arthur

Specialized ML system (investigate purpose).

Model Armour

Security and validation tools for models.

Creating Agent Models

Micro-agents need small, fast models:

  1. Start with large model (from text-models/)
  2. Fine-tune on specific task
  3. Quantize (FP32 → INT8)
  4. Optimize for latency
  5. Store in models/agent-models/

Target specs:

  • Size: <500MB
  • Latency: <100ms
  • Accuracy: >90%

Next Steps

  1. Catalog all models in image-models/
  2. Catalog all models in text-models/
  3. Create agent-specific models
  4. Set up MLflow registry
  5. Build training pipeline