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-Specialized-Domains-v1")model = AutoModelForCausalLM.from_pretrained("SZLHOLDINGS/SZL-Specialized-Domains-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.
Training (MEASURED)
- Base: SZLHOLDINGS/szl-receiptagent-qwen35-0.8b-sft-v3
- Dataset:
SZLHOLDINGS/specialized-domains-corpus-v1 (117 examples)
- Method: QLoRA SFT via Unsloth + TRL on NVIDIA A6000 (Massed Compute), merged 16-bit push
- Wave:
szl-specialized-domains-w22 — completed, WAVE_EXITED_RC=0 (see SZLHOLDINGS/wave-logs)
- Trained by: SZL Holdings (betterwithage)
Evaluation status: NOT_RUN
No held-out evaluation or benchmark scores exist for this model yet. No capability
claims are made. Absence of eval is not evidence of quality; treat outputs as
unvalidated until eval receipts are published to SZLHOLDINGS/model-eval-receipts.
Limitations
- Small corpus (117 examples) — narrow domain coverage, high overfit risk
- No abstention counterweight training in this wave
- No hallucination/confabulation measurement yet
- Not published as production-eligible; no x402 endpoint serves this model
Honest-use doctrine
Per SZL doctrine: model output is an untrusted proposal. Any consequential action
must pass a separate deterministic controller and human approval boundary.
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_specialized_domains_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:
a7feecbed75d9bec1bb34a42574233f6641ef23a. The prior card remains in revision history.
- Observed repository creation date:
UNAVAILABLE.
- Observed repository contents: 10 files (1 weight files, 4 config/tokenizer files, 4 other files).
- 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:
1ca7a10a068ccdc43470aee225b0b346fe061ec4. The prior card remains in revision history.
- Observed repository creation date:
UNAVAILABLE.
- Observed repository contents: 10 files (1 weight files, 4 config/tokenizer files, 4 other files).
- 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.