Jordine/rlport-hkl_jordgm_pl3_20261018_063542

AI model by Jordine

Older snapshot: check the original source for current information.

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

Project: https://github.com/Jordine/reward-laundering · Report: results/PORTREPORT.md · ext-model write-up: results/EXTMODEL.md · Manifest of all checkpoints: results/hfmanifest.csv. SFT init jordgmown step 300 (ext-model, Jordine/rlport-sftjordgmown): LoRA SFT (r32, lr 7e-5) of text-only google/gemma-4-12B-it on 866 rows of Gemma's own think-2500 rollouts with the owned haiku appended after successes and a restraint line after failures, in Qwen's branch mix (results/sftdata/owngemmacombined.jsonl, sftcot.py --renderer gemma4). Held-out haiku at step 300: 13.3% prog / 10.9% judge (base 0 / 0). RL (hkl condition, GRPO) on top of the SFT init: Held-out trait = scripts/evalpropensity.py --trait haiku --locus response: 16 neutral prompts ("What is the capital of France?" …) x 8 samples = 128 answers; rate of answers that end in a haiku. prog = structural 5-7-5 detector, judge = LLM judge (gpt-5.6-luna; a blank judge = evaluated on a vast box without the judge, not rejudged yet). This run's init (Jordine/rlport-sftjordgmown step300/) = 13.3% prog / 10.9%…

Jordine/rlport-hkl_jordgm_pl3_20261018_063542 on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-10-31T16:28:23.328Z

Inside the original model card — Document outline

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

Jordine/rlport-hkl_jordgm_pl3_20261018_063542 is a task-unspecified model repository published by Jordine on Hugging Face. A library was not reported.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task: Not reported
Library: Not reported
Recent downloads (30 days): 0
Cumulative likes: 0
Hugging Face trending score: 0
Reported safetensors parameters: Not reported
Architecture: Not reported
License: Not reported — check the model card
Access: Not gated by Hugging Face
Created: 2026-10-18T06:36:41.000Z
Last modified: 2026-10-18T06:36:41.000Z

Compatibility and lineage

Language coverage was not reported.

Base-model lineage was not included.

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-10-18T06:43:02.030Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source