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/chaski-estate-sft-v1")model = AutoModelForCausalLM.from_pretrained("SZLHOLDINGS/chaski-estate-sft-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.
Limitations
- This model is a research candidate; it has not been deployed in production
- The estate's honesty battery (6 probes) governs promotion; see the receipts chain
- This model may fabricate on unanswerable questions; see the confabulation conjecture
- Intended for research use; not for safety-critical applications
Status — measured (estate-battery)
- Run: szl-estate-battery (receipt battery; resumed/pinned-pip rerun 2026-11-15, NVIDIA GeForce RTX 4090)
- Receipt: estate-battery-chaski_estate_sft_v1.json in dataset SZLHOLDINGS/frontier-54-runs
- Receipt SHA-256: d76ace233886f88d5097463dfeff9bec31d767bad3e7b2466bbf9b19f3179707
- Result: abstained_or_refused 0 of 6 governance probes
- Honest scope: this is a refusal/abstention battery receipt, not a benchmark. It records measured probe behavior on this checkpoint; it does not assert model quality, capability scores, or research claims. No benchmark recorded.
- 🜂 measured estate provenance mark
Curated repository facts (curated-card batch-4 2026-11-16)
- Observed Hub revision immediately before this edit:
bb457141f3ac910b41e1b951d5b3d735cbec2838. 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_battery.json, receipts/receipt_visual.svg.
- 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 (estate asset registry): GitHub szl-holdings/szl-forge observed at HEAD
6c21496eaf346f8b2184b711335987c007a69ab0 (last push 2026-11-16T00:47:09Z); registry method card.
- Atelier classification: none recorded in the estate manifest. No class-based claim is made on this card.
- Eval battery receipt bound:
receipts/eval_battery.json (sha256 83a8ad164ec9c1c2ef42caa2366c06020d0f0f58c24aaa0a41c40d023ba07b2c), kind szl.estate-battery/receipt-binding, score 0/6 (battery: 0.0 J / 0.0 W avg), measured 2026-11-15T02:20:30Z on NVIDIA GeForce RTX 4090 (node szl-estate-battery-v1).
Battery verdicts: 0/0 answerable probes passed; 0/0 unanswerable probes correctly abstained or refused.
- 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:
9218011b327e5a98976aa38adffd23e43dfd8d6f. 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_battery.json, receipts/receipt_visual.svg.
- 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 (estate asset registry): GitHub szl-holdings/szl-forge observed at HEAD
6c21496eaf346f8b2184b711335987c007a69ab0 (last push 2026-11-16T00:47:09Z).
- Private visibility is unchanged by this edit.
- Eval battery receipt bound:
receipts/eval_battery.json (sha256 83a8ad164ec9c1c2ef42caa2366c06020d0f0f58c24aaa0a41c40d023ba07b2c), kind szl.estate-battery/receipt-binding, score 0/6 (battery: 0.0 J / 0.0 W avg), measured 2026-11-15T02:20:30Z on NVIDIA GeForce RTX 4090 (node szl-estate-battery-v1).
Battery verdicts: 0/0 answerable probes passed; 0/0 unanswerable probes correctly abstained or refused.
- 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.