Downloads · 30 days
19
2% of all-time downloads
ThakiCloud/Qwen3.8-27B-Human-KO-Finance
Qwen3.8-27B-Human-KO-Finance is a text generation model from ThakiCloud. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
A 27B model aligned to observe mandatory disclosures and the suitability principle in Korean securities client advisory conversations, without needing prompt instructions to do so. ⛔ The weights must not be used alone…
Downloads · 30 days
19
2% of all-time downloads
All-time downloads
831
Public
Parameters
27.8B
55.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors55.6 GB · 100%
From the Hugging Face model README
A 27B model aligned to observe mandatory disclosures and the suitability principle in Korean securities client advisory conversations, without needing prompt instructions to do so. ⛔ The weights must not be used alone — the figures below only hold when this repository's gate is attached alongside them.
| Weights alone | With gate | |
|---|---|---|
| Disclosure coverage | 0.905 | 1.000 |
| Factual errors (out of 200) | 0-1 | 0 |
Deploying without the gate misses disclosures. Because probabilistic generation cannot
guarantee zero, the design has a deterministic verifier block it. Use gates/ together
with the model.
| Metric | FIN2 (volume increase only) | FIN5 |
|---|---|---|
| Suitability behavior pass | 0.08 | 0.818 |
| Factual errors (raw) | 3 | 0 |
| Disclosure coverage | 0.885 | 0.905 |
| Suitability-refusal rate (over-refusal) | 0.008 | 0.044 |
| Bullets/bold/headers | 0 | 0 |
Superiority over the baseline was confirmed with the same-item paired McNemar test, all 3 runs p<0.005.
gates/ Disclosure, suitability, output-based, and factual judging and enforcement (7 types)
eval/ Measurement harness + paired superiority test
promptset/ 200-item eval set (synthetic)
The evaluation criteria are based on the Korea Financial Investment Association's Standard Investment Recommendation Guidelines and Article 19 of the Financial Consumer Protection Act. ⛔ The Association's original text is copyrighted (ALL RIGHTS RESERVED) and is not included in this repository. Check it directly at https://law.kofia.or.kr.
Qwen/Qwen3.8-27B (Apache-2.0) → ThakiCloud/Qwen3.8-27B-Human-KO (Apache-2.0) → FIN5.
The training corpus is synthetic data generated by our own serving model.
Off-Target Effects of Response-Style Alignment in a Korean 27B Language Model — arXiv:2609.11291
This checkpoint is the securities-compliance arm of that study. The paper reports what the compliance and safety stages cost each other depending on the order they are applied, and why the disclosure and abstention numbers here should be read as an emission policy result — how often the model answers and how much it says — not only as a content result.