SmolLM2-360M-Instruct-Mem-Cat/README.md

base_model, library_name, license, tags, language

base_model	library_name	license	tags	language
HuggingFaceTB/SmolLM2-360M-Instruct	transformers	apache-2.0	memory-router phone-assistant classification	en

Hermie Assistant - Memory Router

Sys prompt:

"\n{"fact":str|null,"retrieve":bool,"tool":bool,"emotion":str}\nfact: durable personal fact, compressed. null if nothing to store."

Output format:

{"fact":str|null,"retrieve":bool,"tool":bool,"emotion":str}

Tool:

Basic tool intent detection. For context for larger LLM.

Retrieve:

Binary gate that engages the embedding model for memory retrieval.

Emotion

Emotional response for larger LLM, persistent accross chats.

Fine-tuned from SmolLM2-360M-Instruct for personal assistant memory classification.