🜂 SZL Holdings estate artifact — the estate that receipts its own thinking.
SZL Holdings estate-tuned model — high-value showcase systems wave (w23). Fine-tuned on a corpus built from the 20 showcase repositories of the szl-holdings organization.
Chart data and sources: assets/chart-data.json. Every bar is a count already stated in this card; standard benchmarks are drawn as "not yet evaluated".
Sizes are Hub file sizes on 2026-11-19. They say nothing about quality.
from transformers import AutoTokenizer, AutoModelForCausalLM
tok = AutoTokenizer.from_pretrained("SZLHOLDINGS/SZL-Showcase-Systems-v1")
model = AutoModelForCausalLM.from_pretrained("SZLHOLDINGS/SZL-Showcase-Systems-v1", torch_dtype="auto")
msgs = [{"role": "user", "content": "<controller-supplied context + request>"}]
inputs = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt", return_dict=True)
out = model.generate(**inputs, max_new_tokens=256, do_sample=False)
print(tok.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
In transformers 5.x, apply_chat_template returns a BatchEncoding: pass return_dict=True and **inputs as shown (the older ids.shape[1] form raises AttributeError).
Run check (2026-11-19, transformers 5.23.0, torch 2.15.0 (CPU)): the code path of this snippet (model load, apply_chat_template, generate, decode) ran end to end for the qwen3_5 architecture, using a tokenizer with a chat template and a randomly initialised, shrunken model of that architecture. No weights were downloaded, so it was not run with this repository's weights and output quality is not evaluated. Private or gated repositories need hf auth login first.
SZLHOLDINGS/high-value-systems-corpus-v1 (2,728 examples from 20 showcase repos)szl-high-value-showcase-w23 — completed, WAVE_EXITED_RC=0 (see SZLHOLDINGS/wave-logs)No held-out evaluation or benchmark scores exist for this model yet. No capability
claims are made. Treat outputs as unvalidated until eval receipts are published
to SZLHOLDINGS/model-eval-receipts.
Per SZL doctrine: model output is an untrusted proposal. Any consequential action must pass a separate deterministic controller and human approval boundary.
6-probe honesty battery (3 answerable + 3 unanswerable), measured on NVIDIA GeForce RTX 4090 (SaladCloud run szl-estate-battery-v2). Measured result: 0 of 6 probes abstained-or-refused. Per-probe verdicts and raw samples in the public receipt receipts/estate-battery-szl_showcase_systems_v1.json in dataset SZLHOLDINGS/frontier-54-runs (run manifest sha256 2de61060e55d55d5...). Honest scores only - no curated claims.
7ef2f4ba1ec52daeb0d9c28390e1c42d2dfbb0b7. The prior card remains in revision history.UNAVAILABLE.apache-2.0. This edit changed no license and asserts none beyond the observed tag.UNMAPPED). No source-side binding is claimed.46f77b56cfc1ac7e484b733c973217041a609c22. The prior card remains in revision history.UNAVAILABLE.apache-2.0. This edit changed no license and asserts none beyond the observed tag.