2b Models

This very WIP page (v1 26.0610) describes model internals.

The agent and the NN are typically packed into a model that has an API that makes it possible for existing software to use the model as a “helpful” assistant. The internal agent (iAgent) that has been programmed to interact with the transformer (TF) via a very specific token-only protocol. The TF has also been trained to follow this protocol.

NOTE »> (1) Tiny agentic AI model demo, (2) Backdoor in a model

Models in the AI ecosystem

TOC

xxxxx

2b.1 Model concepts

(2b.1b 2025 demos)

2b.2 Tiny demos

(from 2b.6 LLM demos)

2b.2b Building models

For specific domains. How do I create a model for a specific purpose? Domain-specific models, Synthetic data, Custom TF, Custom CNN.

2b.3 Modifying models

Modifying/customizing/fine-tune. LoRA, Adapters, Domain Specialization

2b.4 Running models locally

This is actually one of the strongest sections because it matches your current interests exactly. HuggingFace, Ollama, Local Models, etc. How do I own and operate AI?

26.0613 (v1 26.0610)