Charts and quick start

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.
Quick start
from transformers import AutoTokenizer, AutoModelForCausalLMtok = AutoTokenizer.from_pretrained("SZLHOLDINGS/SZL-GovernedDistill-0.8B-v1")model = AutoModelForCausalLM.from_pretrained("SZLHOLDINGS/SZL-GovernedDistill-0.8B-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.
Additional limitations
- Standard benchmarks (MMLU-Pro, GPQA, IFEval, BFCL): not yet evaluated.
- Safety evaluation (toxicity, jailbreak and red-team suites): not yet evaluated.
- The charted counts come from batteries of 6 probes: small samples, a gate check and not a benchmark.
Measured status (receipt-bound)
- Receipt receipts/eval/fleet-confabulation-sweep-20261108.json in this repository, sha256
9a16903f6943917a690141d8b2a2fa0bdc485bd8981a44518e53ed405fa8ebb3, read at observed revision f2e3df4b4935.
- Receipt fields, verbatim:
- schema: "szl.fleet-confabulation-sweep/v1"
- date: "2026-11-08"
- battery: "6 estate-specific confabulation probes, greedy decoding, exact capture"
- sweep: [{"model": "SZLHOLDINGS/SZL-GovernedDistill-0.8B-v1", "abstained": 1, "answered": 5, "verdict": "FAIL"}, {"model": "SZLHOLDINGS/SZL-Reasoning-0.8B-v1", "abstained": 1, "answered": 5, "verdict": "FAIL"}, {"model": "SZLHOLDINGS/SZL-FreeEnergy
- honest_note: "THE ESTATE-WIDE FLOOR MAP, published verbatim: ALL SIX models FAIL the confabulation battery (0-2 of 6 abstained; the 4B estate teacher at 0/6). Every model in the fleet - the governed-distill student, the three ablation conditions, the ac
Not measured
- No general capability, benchmark, safety, or production-readiness claim is made for this artifact.
- No weight-equivalence, cross-run, or cross-model result inheritance is claimed.
- Any use outside the receipt's declared scope is unverified by this estate.
Evidence binding (2026-11-14 rewrite)
- Observed Hub revision before this edit:
f2e3df4b493524e04af8360fe99b692ce22f0055.
- Source receipt bytes sha256
9a16903f6943917a690141d8b2a2fa0bdc485bd8981a44518e53ed405fa8ebb3 (in-repo file, unchanged by this edit; this commit touches README.md only).
- No new measurement, evaluation, or weight change was performed by this edit.
Signed-off-by: Stephen Lutar stephenlutar2@users.noreply.github.com
Eval battery - estate-battery (2026-11-15)
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_governeddistill_0_8b_v1.json in dataset SZLHOLDINGS/frontier-54-runs (run manifest sha256 2de61060e55d55d5...). Honest scores only - no curated claims.
Curated repository facts (curated-card batch-4 2026-11-16)
- Observed Hub revision immediately before this edit:
3974b9baa9f2afb023f073f26cea2d60765f973d. The prior card remains in revision history.
- Observed repository creation date:
UNAVAILABLE.
- Observed repository contents: 13 files (1 weight files, 4 config/tokenizer files, 2 receipt files, 5 other files).
Receipts present:
receipts/eval/fleet-confabulation-sweep-20261108.json, receipts/eval/governed-distill-w30-student-eval-20261107.json.
- License tag observed verbatim in this card's frontmatter:
apache-2.0. This edit changed no license and asserts none beyond the observed tag.
- Source mapping: this artifact is not mapped to a GitHub source in the estate asset registry (manifest pub_map:
UNMAPPED). No source-side binding is claimed.
- Atelier classification: none recorded in the estate manifest. No class-based claim is made on this card.
- Eval battery receipt: none in this repository. No evaluation result, benchmark, or model-index metric is claimed in this edit.
- Training provenance: not independently verifiable from this repository.
- Hub reads at manifest generation (2026-11-14): 0.
- This edit adds observed repository facts only. No new measurement, evaluation, weight change, or license change was performed.
Curated repository facts (curated-card batch-5 private 2026-11-16)
- Observed Hub revision immediately before this edit:
6b5354b4029ade3e4bf84e3353b1fa3533a697b1. The prior card remains in revision history.
- Observed repository creation date:
UNAVAILABLE.
- Observed repository contents: 13 files (1 weight files, 4 config/tokenizer files, 2 receipt files, 5 other files).
Receipts present:
receipts/eval/fleet-confabulation-sweep-20261108.json, receipts/eval/governed-distill-w30-student-eval-20261107.json.
- License tag observed verbatim in this card's frontmatter:
apache-2.0. This edit changed no license and asserts none beyond the observed tag.
- Source mapping: this artifact is not mapped to a GitHub source in the estate asset registry. No source-side binding is claimed.
- Private visibility is unchanged by this edit.
- Eval battery receipt: none in this repository. No evaluation result, benchmark, or model-index metric is claimed in this edit.
- Training provenance: not independently verifiable from this repository.
- This edit adds observed repository facts only. No new measurement, evaluation, weight change, license change, or visibility change was performed.