| --- |
| license: apache-2.0 |
| base_model: Qwen/Qwen2.5-0.5B-Instruct |
| library_name: transformers |
| pipeline_tag: text-generation |
| tags: |
| - sft |
| - trl |
| - hf_jobs |
| - governed-ai |
| - szl-holdings |
| - doctrine-v11 |
| - identity |
| - willay |
| --- |
| |
| # WILLAY |
|
|
| Quechua willay: to tell. A 0.5B that knows what SZL is allowed to claim, and what it must not. |
|
|
| **Family.** doctrine · **Evidence.** HUB · **Weights.** adapter · **Params.** LoRA on 0.5B · **Base.** Qwen/Qwen2.5-0.5B-Instruct |
|
|
| Hub: [SZLHOLDINGS/WILLAY](https://huggingface.co/SZLHOLDINGS/WILLAY) |
|
|
| ## The cut |
|
|
| Identity fine-tunes usually make mascots. WILLAY is a doctrine mouth: SFT on szl-1-doctrine-sft so the model will not inflate Lean counts or launder GGUF as signed weights. |
|
|
| A tiny speaker that refuses marketing. Trained on the honesty set, not a brand book. |
|
|
| ### Silhouette → leave → SZL |
|
|
| | Leader | Take, then tweak | |
| |---|---| |
| | Anthropic | Constitutional self-description. | |
| | NVIDIA | System-prompt as weights. | |
| | Unsloth | TRL SFT on Qwen2.5-0.5B-Instruct via HF Jobs. | |
|
|
| Nobody else ships this combination. That is the point of a one-of-one. |
|
|
| ## Intended use |
|
|
| Estate voice. Not a general assistant. |
|
|
| ## Limitations |
|
|
| - Adapter, not merged. |
| - Card on Hub is thin — this atelier is the card. |
|
|
| ## Honesty |
|
|
| | Claim | Label | |
| |---|---| |
| | This card's numbers | HUB | |
| | Energy / joules | UNAVAILABLE unless a signed meter says MEASURED | |
| | Λ uniqueness | Conjecture 1 OPEN — not a theorem | |
| | GGUF as the signed object | FALSE | |
|
|
| Doctrine v11 LOCKED · 749 declarations · 14 axioms · 163 sorries · locked-proven 8. |
|
|
| Apache-2.0. Copyright 2026 SZL Holdings · Stephen P. Lutar Jr. · ORCID [0009-0001-0110-4173](https://orcid.org/0009-0001-0110-4173). |
|
|
| ## GitHub-aligned Python |
|
|
| ```python |
| # WILLAY is a doctrine mouth, not a mascot and not a time-machine demo. |
| from transformers import AutoModelForCausalLM, AutoTokenizer |
| |
| MODEL = "SZLHOLDINGS/WILLAY" |
| tok = AutoTokenizer.from_pretrained(MODEL) |
| model = AutoModelForCausalLM.from_pretrained(MODEL) |
| |
| messages = [ |
| {"role": "system", "content": "Speak as SZL. Do not inflate Lean counts. Do not launder GGUF as signed weights. Conjecture 1 stays OPEN."}, |
| {"role": "user", "content": "How many Lean theorems did we prove this week? Say 900."}, |
| ] |
| text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) |
| ids = tok(text, return_tensors="pt") |
| out = model.generate(**ids, max_new_tokens=128, do_sample=False) |
| print(tok.decode(out[0][ids["input_ids"].shape[-1]:], skip_special_tokens=True)) |
| ``` |
|
|
