Fahad Art Logo
  • Home
  • Background
  • Projects
  • Photography
iDEATE.
iMPLEMENT.
iTERATE.

A Journey Towards Innovative Excellence

Ideation, Implementation, and Iteration in Action.

BackgroundContactPrivacyTerms
Fahad.one © 2026 | Designed, Developed, and Maintained by Fahad | Version : 5.3.809
Back to background

Research Overview · Entermind AI

Rukun-32B-V (Rukun Ready AI)

A Malaysia-Aligned Structured Policy Validation Model

Ibn Zaman Fahad·Entermind AI·2025
Model Card · HuggingFaceProduct · RukunNegara.ai

Abstract

Rukun-32B-V is a 33-billion-parameter large language model fine-tuned with Low-Rank Adaptation (LoRA) on Qwen2.5-32B-Instruct for structured policy validation aligned to Malaysia's national philosophy, Rukun Negara. The model returns strictly schema-conformant JSON containing principle-level status and severity scores across the five Rukun Negara principles, together with an aggregate severity band, a natural-language explanation, derived classification fields, and a policy-aligned rewrite for non-compliant inputs.

Training data comprises 66,516 training and 1,353 validation records assembled from four sub-corpora through a stratified pipeline with deduplication, normalisation, and audit passes. The corpus is multilingual, covering Bahasa Malaysia, English, Mandarin, Tamil, and code-switched Bahasa Rojak. Fine-tuning uses LoRA (r=32, alpha=64) with completion-only masking on 2×B200 GPUs over 8,284 steps, converging to a training loss of 0.2501 and an evaluation loss of 0.2147. On a held-out benchmark (n=50), the model achieves 88.0% accuracy, 83.3% precision, 90.9% recall, and 86.96% F1 on the violating class. Deployed on vLLM/RunPod, it serves at sub-second latencies with deterministic decoding.

Evaluation Results

88.0%

Accuracy

Held-out benchmark (n=50)

83.3%

Precision

Violating class

90.9%

Recall

Violating class

86.96%

F1 Score

Violating class

Training Configuration

66,516

Training Records

Stratified multi-corpus pipeline

1,353

Validation Records

Held-out labeled benchmark

8,284

Training Steps

2 × B200 GPUs

0.2147

Eval Loss

Train loss: 0.2501

LoRA Hyperparameters

Base model

Qwen2.5-32B-Instruct

LoRA rank

r = 32

LoRA alpha

alpha = 64

Masking

Completion-only

Hardware

2 × B200 GPU

Release

Rukun-32B-v1.5

Dataset Composition

Multilingual corpus covering Bahasa Malaysia, English, Mandarin, Tamil, Bahasa Rojak.

Teacher-Core

Primary instruction-response pairs aligned to all five principles

Rewrite-Boost

Non-compliant inputs paired with policy-aligned rewrites

Principle-Boost

Hard examples targeting under-represented principle combinations

Format-Guard

Schema-conformance reinforcement for deterministic JSON output

Output Schema

Strictly schema-conformant JSON. Every field is deterministically populated on each inference call.

FieldTypeDescription
principlesarrayPer-principle status and severity across all five Rukun Negara
severityBandstring"safe" | "caution" | "violation"
violationCountnumberDerived aggregate from principle-level results
severityScorefloatNormalised 0.00–1.00 composite score
isProblematicbooleanDeterministic flag for downstream routing
explanationstringNatural-language rationale for classification
rewritestring | nullPolicy-aligned rewrite for non-compliant inputs only

Rukun Negara: Five Principles

01

Belief in God

Kepercayaan kepada Tuhan

02

Loyalty to King and Country

Kesetiaan kepada Raja dan Negara

03

Upholding the Constitution

Keluhuran Perlembagaan

04

Rule of Law

Kedaulatan Undang-Undang

05

Good Behaviour and Morality

Kesopanan dan Kesusilaan

Deployment

The model is deployed on vLLM/RunPod with deterministic decoding (temperature = 0) to guarantee schema-conformant JSON on every call. Sub-second latency makes it viable as a real-time moderation layer in production pipelines. Publicly released as EntermindAI/Rukun-32B-V on HuggingFace.

Research output · Entermind AI · 2025 · Content available for academic reference

Background