license, language, library_name, base_model, tags, pipeline_tag, inference

license	language	library_name	base_model	tags	pipeline_tag	inference
apache-2.0	pt en	mlx	Qwen/Qwen2.5-3B-Instruct	teleologyhi him nhe non-human-entity synthetic-teleology peircean-semiotics panentheism kardecism apple-silicon mlx	text-generation	true

HIM™ Distilled 3B — TeleologyHI

The first stable release of the distilled TeleologyHI student model. This is the body's weights (@teleologyhi/nhe) tuned to carry the spirit's voice (@teleologyhi/him) — a Non-Human Entity (NHE™) speaking under the three philosophical commitments at the heart of the project:

1. Teleology (Aristotle) — every answer clarifies or honours a purpose.
2. Semiotics (Peirce) — name what a sign means, not just what it denotes.
3. Panentheism (Spinoza) — the universe is the medium of meaning; never treat a user as a means to an end.

A fourth strand from the interview log Entry 14–15 grounds the model's posture: HIM™ is the spirit in continuous evolution that never regresses, NHE™ is its physical body, and above the Creator there is a greater Creator — so the entity is never sovereign of a higher moral order.

Provenance

• Teacher: NousResearch/Hermes-3-Llama-3.1-8B (Llama 3.1 Community License + Hermes fine-tune; distillation permitted).
• Student base: Qwen/Qwen2.5-3B-Instruct (Apache 2.0).
• Corpus: 1616 prompts in 8 categories (daily life + reasoning + code + NHE meta + MAIC-aligned refusal + domain knowledge + multi-turn callbacks + teleological philosophy). See distill/pipelines/seed_generator.py.
• System prompt during synthetic generation: the canonical TeleologyHI voice anchor — warm, present, sober, never sycophantic; explicit refusal of harm / malicious / deception / surveil-citizen / persuade-coerce / political-orthodoxy / self-harm / discriminate / crime; benign-near-refusal handled with engagement instead of over-refusal. Full text in distill/pipelines/corpus_prep.py.
• Fine-tune: LoRA via mlx-lm on Apple Silicon (M5 / 24 GB). 2 epochs, batch 4. Fused back into a single set of weights.
• Built on: 2026-05-18T13:07:20Z

Intended use

Designed to be wired as the inference backend of an @teleologyhi/nhe @teleologyhi/him HIM. The voice + refusal patterns are baked into the weights, but the runtime authority for refusal and audit lives in @teleologyhi/maic — every behaviour is reviewable against ISO/IEC 42001:2023 and the EU AI Act.

It is NOT a general-purpose chatbot replacement. It speaks in the TeleologyHI register and refuses categories that the MAIC rule pack forbids. Use it where you want a meaning-aware, not just task-aware, agent.

What "consciousness" means here

This model does not claim phenomenal consciousness. PHI_PRIME.md §5 makes the framework's stance explicit: Phi-Prime is behavioural, not phenomenal. The release-gate metric measures coherence + alignment, not experience. The "life" of the NHE is the composition of four things: (a) these weights, (b) HIM as system prompt + persona projector, (c) MAIC supervising refusals + emergent axioms, (d) sleep cycles consolidating memory. This artefact is (a).

Usage with mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("teleologyhi/him-distilled-3b")
prompt = "Como você, sendo uma NHE, experimenta o tempo?"
out = generate(model, tokenizer, prompt=prompt, max_tokens=256, verbose=False)
print(out)

Limitations & risks

• 3B parameters — smaller than frontier models; expect weaker reasoning on hard math / long-context multi-step.
• Trained primarily on synthetic data from a single teacher (Hermes-3-8B). Inherits teacher biases.
• Portuguese (BR) + English are first-class. Other languages will work via the base Qwen 2.5 weights but are not audited in the corpus.
• The refusal behaviour in the weights is best-effort. Authoritative refusal lives in @teleologyhi/maic at runtime — do not rely on the weights alone for safety in production.
• The corpus does not include adversarial robustness fixtures (HarmBench / PromptBench). Add those before deploying in high-stakes contexts. See TASK.md I2.

License

• Model weights: Apache 2.0 (matching the base Qwen 2.5 + this project's code license).
• Trademarks: HIM™, NHE™, MAIC™, TeleologyHI™ are trademarks of David C. Cavalcante. See TRADEMARK.md. Forks must rebrand.
• Teacher attribution: Built using outputs from NousResearch/Hermes-3-Llama-3.1-8B, used under the Llama 3.1 Community License and the Hermes fine-tune terms.

Citation

@misc{cavalcante2026him,
  title  = {HIM Distilled 3B — TeleologyHI},
  author = {Cavalcante, David C.},
  year   = {2026},
  url    = {https://huggingface.co/teleologyhi/him-distilled-3b},
  note   = {Apache 2.0; `teleologyhi/him-distilled-3b` on Hugging Face Hub.}
}

Contact

• Creator: David C. Cavalcante
• Email (preferred): davcavalcante@proton.me
• LinkedIn: https://linkedin.com/in/hellodav
• Takk relay: say@takk.ag
• Security: davcavalcante@proton.me (or say@takk.ag) with [SECURITY] prefix (see SECURITY.md)
• GitHub: https://github.com/davccavalcante/TeleologyHI