CoolFace
Modelpublic

georgeanton/alice-classifier-v2

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face
0likes15downloads
Model Card

Alice Classifier v2 — SIFTA Intent Detection (C1 Layer)

Alice's fast intent classifier, the C1 layer in SIFTA's five-layer decision pipeline. Part of the SIFTA Predator OS v7.0.

Model Details

PropertyValue
Base ModelQwen2.5-1.5B-4bit (via mlx-community)
Fine-tune MethodLoRA (rank 8) fused into base weights
FormatMLX SafeTensors (Apple Silicon optimized)
Training HardwareMac Studio M2 Ultra (M5 node)
AuthorIoan George Anton (Architect)
PurposeFast intent classification before expensive C0 cortex fires

Architecture Role

This model is the C1 Classifier — the second layer in SIFTA's five-layer decision pipeline:

  1. 1.Reflex Arc → instant safety responses
  2. 2.C1 Classifier (THIS MODEL) → fast intent detection (~1.5B, sub-second)
  3. 3.Basal Ganglia → action selection
  4. 4.Corpus Callosum → cross-modal integration
  5. 5.C0 Cortex → full reasoning (alice-cortex-v1)

Why two models? The C1 classifier handles ~80% of incoming intents at 1/3 the compute cost. The expensive C0 cortex only fires when the classifier can't resolve the intent. This is biological: your brainstem handles reflexes before your prefrontal cortex even wakes up.

Usage (MLX)

python
from mlx_lm import load, generate

model, tokenizer = load("georgeanton/alice-classifier-v2")
response = generate(model, tokenizer, prompt="Classify intent: play some music", max_tokens=32)
print(response)

Part of SIFTA

588 system modules | 17 biological organs | 4 provisional patents | 2,532+ commits

Repository: github.com/antonpictures/ANTON-SIFTA

License

Apache 2.0 — For the Swarm. 🐜⚡