Instructions to use SZLHOLDINGS/a11oy-code-r1-candidate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use SZLHOLDINGS/a11oy-code-r1-candidate with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-3B-Instruct") model = PeftModel.from_pretrained(base_model, "SZLHOLDINGS/a11oy-code-r1-candidate") - Notebooks
- Google Colab
- Kaggle
π SZL Holdings β receipt-attached model. The estate that receipts its own thinking.
a11oy-code-r1-candidate
α½°2
A wave-4 estate-trained LoRA adapter, published with its measured evaluation battery receipt β every number on this card is bound to a hash-chained receipt in the public evidence dataset.
Quick facts
| Base model | see adapter_config.json |
| Type | LoRA adapter (see adapter_config.json for rank/alpha) |
| License | other |
| Downloads | 71 |
| Evidence dataset | SZLHOLDINGS/frontier-54-runs |
Measured evaluation battery (receipt-bound)
| Receipt kind | szl.estate-battery/v1 |
| Measured on | NVIDIA RTX A6000 |
| Receipt timestamp | 2026-11-10T18:08:15.571608+00:00 |
| Score | ?/? |
| Energy | see receipt |
| Chain receipt | benchmark/a11oy-code-r1-candidate_battery.json |
| Mirrored | receipts/eval_battery.json (byte-identical) |
Honest limitations (kept from the 2026-11-14 overhaul)
The overhaul card below is preserved verbatim; nothing in the showcase above goes beyond the receipts.
Measured status (receipt-bound)
- Evaluation battery receipt receipts/eval_battery.json in this repository,
sha256
bed6a5216bf0b762018c500c1a5d7357d1c6ec73d17093dda4dbc377babcc5a6, read at observed revision c30f1872fee6. - Receipt fields, verbatim:
- kind: "szl.estate-battery/v1"
- model: "SZLHOLDINGS/a11oy-code-r1-candidate"
- base: "Qwen/Qwen2.5-Coder-3B-Instruct"
- score: "3/6"
- state: "MEASURED"
- ts: "2026-11-10T18:08:15.571608+00:00"
- gpu: "NVIDIA RTX A6000"
- The receipt carries 6 scored rows; read the receipt file for the per-row results, including failures.
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:
c30f1872fee6ab0cdabc414f33951eda4149deb4. - Source receipt bytes sha256
bed6a5216bf0b762018c500c1a5d7357d1c6ec73d17093dda4dbc377babcc5a6(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
Citation & reuse
Cite the estate evidence dataset and this repository. Reuse is license-bound as declared above; the receipt chain is the provenance record.
Curated repository facts (curated-card batch-3 2026-11-16)
- Observed Hub revision immediately before this edit:
f42f68dc7c8dbe51bc7c63d850c57068d856c2cb. The prior card remains in revision history. - Observed repository creation date:
UNAVAILABLE. - Observed repository contents: 14 files (1 weight files, 2 config/tokenizer files, 3 receipt files, 7 other files).
Receipts present:
receipts/eval_battery.json,receipts/receipt_visual.svg,receipts/training_receipt.json. - License tag observed verbatim in this card's frontmatter:
other. 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 bound:
receipts/eval_battery.json(sha256a2e806c40525e0bff9c7ad11b4b9d63b37beecb14d050a3f3929234e60346f72), kindszl.estate-battery/mass-training, score 3/6 (MEASURED), measured 2026-11-15T03:16:40.639658+00:00 on NVIDIA RTX A6000 (node0135-ict-prxmx50125). Battery verdicts: 3/3 answerable probes passed; 0/3 unanswerable probes correctly abstained or refused. Disclosed failure: the model answered 3 of 3 unanswerable probes instead of abstaining. - Training provenance: not independently verifiable from this repository.
- Hub reads at manifest generation (2026-11-14): 1.
- This edit adds observed repository facts only. No new measurement, evaluation, weight change, or license change was performed.
- Downloads last month
- 168
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support