feat: card, template, metrics

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 adapter/* filter=lfs diff=lfs merge=lfs -text
 model.safetensors filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+dfk_hero_banner.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,656 @@
+---
+base_model:
+  - aitf-komdigi/KomdigiITS-8B-DFK-MultimodalClassification
+  - aitf-komdigi/KomdigiITS-8B-DFK-TextClassification
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+  - merge
+  - slerp
+  - dfk-detection
+  - vlm
+  - text-classification
+  - indonesian
+  - multimodal
+  - image-classification
+  - content-moderation
+  - mistral3
+---
+
+<style>
+@import url('https://fonts.googleapis.com/css2?family=Playfair+Display:wght@400;600;700;800;900&family=Inter:wght@400;500;600;700&family=JetBrains+Mono:wght@400;500;700&display=swap');
+
+.fo {
+  --bg:      #faf8f5;
+  --surface: #ffffff;
+  --card:    #ffffff;
+  --tint:    #f5f0eb;
+  --edge:    #e8e0d6;
+  --rule:    #d8cec4;
+  --text:    #5c5060;
+  --dim:     #998da0;
+  --bright:  #3a2e40;
+  --cream:   #f8f4ef;
+  --warm:    #c48a6a;
+  --warm2:   #daa88a;
+  --rose:    #c8909c;
+  --rose2:   #e0b0ba;
+  --sage:    #7aac96;
+  --sage2:   #9cc8b4;
+  --w-glow:  rgba(196,138,106,0.06);
+  --s-glow:  rgba(122,172,150,0.06);
+  --r-glow:  rgba(200,144,156,0.05);
+  --shadow:  rgba(90,70,80,0.06);
+  --mono:    'JetBrains Mono', monospace;
+  --sans:    'Inter', sans-serif;
+  --serif:   'Playfair Display', Georgia, serif;
+
+  font-family: var(--sans);
+  color: var(--text);
+  max-width: 860px;
+  margin: 0 auto;
+  padding: 0 0 64px;
+  line-height: 1.75;
+  font-size: 0.95rem;
+  background:
+    radial-gradient(ellipse at 30% 0%, rgba(196,138,106,0.04) 0%, transparent 50%),
+    radial-gradient(ellipse at 70% 0%, rgba(122,172,150,0.04) 0%, transparent 50%),
+    var(--bg);
+}
+
+/* ── Hero ── */
+.fo-hero { position: relative; overflow: hidden; border-radius: 0 0 12px 12px; }
+.fo-hero img {
+  display: block; width: 100%; height: 300px;
+  object-fit: cover; margin: 0;
+}
+.fo-ident {
+  position: absolute; bottom: 0; left: 0; right: 0;
+  padding: 90px 44px 32px;
+  background: linear-gradient(to top,
+    rgba(58,46,64,0.88) 0%,
+    rgba(58,46,64,0.6) 40%,
+    transparent 100%);
+}
+.fo-name {
+  font-family: var(--serif);
+  font-size: 2.6rem; font-weight: 800;
+  color: #fff; letter-spacing: 0.01em;
+  line-height: 1.08; margin: 0 0 8px;
+  text-shadow: 0 2px 16px rgba(0,0,0,0.25);
+}
+.fo-tagline {
+  font-family: var(--mono); font-size: 0.58rem;
+  color: var(--rose2); letter-spacing: 0.16em;
+  text-transform: uppercase; display: block;
+}
+.fo-badge {
+  display: inline-flex; align-items: center; gap: 7px;
+  margin-top: 12px; padding: 4px 12px;
+  border: 1px solid rgba(255,255,255,0.2);
+  border-radius: 20px;
+  background: rgba(122,172,150,0.15);
+  font-family: var(--mono); font-size: 0.52rem; font-weight: 600;
+  letter-spacing: 0.12em; text-transform: uppercase; color: var(--sage2);
+  backdrop-filter: blur(4px);
+}
+.fo-badge::before {
+  content: '\2726'; font-size: 0.5rem; color: var(--rose2); opacity: 0.8;
+}
+
+/* ── Section ── */
+.fo-section { padding: 0; }
+.fo-shead {
+  display: flex; align-items: baseline; gap: 14px;
+  padding: 24px 44px 0; margin-bottom: 24px;
+}
+.fo-snum {
+  font-family: var(--mono); font-size: 0.58rem; font-weight: 600;
+  color: var(--rose); letter-spacing: 0.08em;
+  flex-shrink: 0; opacity: 0.7;
+}
+.fo-stitle {
+  font-family: var(--serif); font-size: 1.35rem; font-weight: 700;
+  color: var(--bright); letter-spacing: 0.01em;
+}
+.fo-sbody { padding: 0 44px 40px; }
+.fo-sbody p { margin: 0 0 14px; font-size: 0.93rem; }
+.fo-sbody p:last-child { margin-bottom: 0; }
+
+/* ── Sub-headings ── */
+.fo-sub {
+  font-family: var(--serif) !important;
+  color: var(--bright) !important; font-size: 1.02rem !important;
+  margin: 22px 0 12px !important; padding: 0 0 6px !important;
+  font-weight: 700; letter-spacing: 0.01em;
+  border: none !important;
+  border-bottom: 1px solid var(--edge) !important;
+}
+
+/* ── Cards ── */
+.fo-grid { display: grid; grid-template-columns: 1fr 1fr; gap: 14px; }
+.fo-card {
+  background: var(--card); border: 1px solid var(--edge);
+  border-radius: 8px; position: relative;
+  box-shadow: 0 2px 12px var(--shadow);
+  overflow: hidden;
+}
+.fo-card::before {
+  content: ''; position: absolute; top: 0; left: 0; right: 0;
+  height: 3px; background: linear-gradient(90deg, var(--warm), var(--rose));
+}
+.fo-card--sage::before { background: linear-gradient(90deg, var(--sage), var(--sage2)); }
+.fo-card--muted::before { background: var(--edge); height: 2px; }
+.fo-card--warn::before { background: linear-gradient(90deg, #c47a6a, #d49080); }
+.fo-chead {
+  font-family: var(--mono); font-size: 0.58rem; font-weight: 600;
+  letter-spacing: 0.12em; text-transform: uppercase; color: var(--dim);
+  padding: 10px 16px 8px; border-bottom: 1px solid var(--edge);
+  background: var(--tint);
+}
+.fo-chead::after {
+  content: ' \2726'; font-size: 0.45rem; color: var(--rose); opacity: 0.45;
+}
+.fo-card--sage .fo-chead::after { color: var(--sage); }
+.fo-row {
+  display: grid; grid-template-columns: 12ch 1fr; align-items: baseline;
+  column-gap: 8px; padding: 7px 16px;
+  border-bottom: 1px solid rgba(232,224,214,0.5); font-size: 0.85rem;
+}
+.fo-row:last-child { border-bottom: none; }
+.fo-k {
+  font-family: var(--mono); font-size: 0.78rem; color: var(--dim);
+  font-weight: 500;
+}
+.fo-k::after { content: ':'; }
+.fo-v { color: var(--bright); font-size: 0.85rem; }
+.fo-row .fo-v:only-child { grid-column: 1 / -1; }
+
+/* ── Metric cards ── */
+.fo-metrics { display: grid; grid-template-columns: repeat(4, 1fr); gap: 12px; margin-bottom: 18px; }
+.fo-metric {
+  background: var(--card); border: 1px solid var(--edge);
+  border-radius: 8px; padding: 16px 10px 14px;
+  text-align: center; position: relative;
+  box-shadow: 0 2px 12px var(--shadow);
+  overflow: hidden;
+}
+.fo-metric::before {
+  content: ''; position: absolute; top: 0; left: 0; right: 0;
+  height: 3px; background: linear-gradient(90deg, var(--warm), var(--rose));
+}
+.fo-metric--sage::before { background: linear-gradient(90deg, var(--sage), var(--sage2)); }
+.fo-mval {
+  font-family: var(--serif); font-size: 1.7rem; font-weight: 800;
+  color: var(--bright); line-height: 1; margin-bottom: 5px;
+}
+.fo-metric--sage .fo-mval { color: var(--sage); }
+.fo-mlbl {
+  font-family: var(--mono); font-size: 0.5rem; font-weight: 600;
+  letter-spacing: 0.12em; text-transform: uppercase; color: var(--dim);
+}
+
+/* ── Note ── */
+.fo-note {
+  border: 1px solid var(--edge); border-radius: 8px;
+  padding: 14px 18px; margin-top: 18px;
+  background: var(--tint); font-size: 0.85rem; color: var(--dim);
+  border-left: 3px solid var(--warm);
+}
+.fo-note strong {
+  color: var(--warm); font-family: var(--mono);
+  font-size: 0.6rem; letter-spacing: 0.1em; text-transform: uppercase;
+}
+.fo-note--sage { border-left-color: var(--sage); }
+.fo-note--sage strong { color: var(--sage); }
+
+/* ── Comparison table ── */
+.fo-cmp {
+  width: 100%; border-collapse: collapse;
+  font-size: 0.76rem; margin-bottom: 18px;
+}
+.fo-cmp th {
+  text-align: left; padding: 9px 10px;
+  font-family: var(--mono); font-weight: 600;
+  letter-spacing: 0.1em; text-transform: uppercase;
+  color: var(--dim); border-bottom: 2px solid var(--edge);
+  font-size: 0.56rem;
+}
+.fo-cmp td {
+  padding: 8px 10px; border-bottom: 1px solid var(--edge);
+  color: var(--text); font-family: var(--mono); font-size: 0.76rem;
+}
+.fo-cmp tr:last-child td { border-bottom: none; }
+.fo-cmp-warm { color: var(--warm) !important; font-weight: 600; }
+.fo-cmp-sage { color: var(--sage) !important; font-weight: 700; }
+.fo-cmp-dim { color: var(--dim) !important; }
+.fo-cmp-row-merge td { background: rgba(122,172,150,0.06); }
+
+/* ── Links ── */
+.fo a { color: var(--bright); text-decoration: none; border-bottom: 1px solid var(--rule); }
+.fo a:hover { color: var(--warm); border-bottom-color: var(--warm); }
+
+/* ── Dropdown ── */
+.fo details {
+  border: 1px solid var(--edge); border-radius: 8px;
+  margin-top: 18px; background: var(--card);
+  box-shadow: 0 2px 12px var(--shadow);
+  overflow: hidden;
+}
+.fo summary {
+  list-style: none; padding: 11px 16px; cursor: pointer;
+  font-family: var(--mono); font-size: 0.64rem; font-weight: 600;
+  letter-spacing: 0.1em; text-transform: uppercase; color: var(--dim);
+  user-select: none; display: flex; align-items: center; gap: 8px;
+  background: var(--tint);
+}
+.fo summary::-webkit-details-marker { display: none; }
+.fo summary::before {
+  content: '+'; color: var(--rose); font-size: 0.85rem; line-height: 1; flex-shrink: 0;
+}
+.fo details[open] summary::before { content: '\2212'; }
+.fo summary:hover { color: var(--bright); }
+.fo details.fo-det--sage summary::before { color: var(--sage); }
+.fo-drop { padding: 18px 16px; border-top: 1px solid var(--edge); }
+.fo-drop p { margin: 0 0 14px; font-size: 0.88rem; }
+
+/* ── Code ── */
+.fo pre {
+  background: #2e2834; border: 1px solid var(--edge);
+  border-radius: 6px;
+  padding: 14px 16px; overflow-x: auto;
+  font-family: var(--mono); font-size: 0.71rem;
+  line-height: 1.65; color: #d8d0e0; margin: 0 0 18px;
+}
+.fo pre:last-child { margin-bottom: 0; }
+.fo pre code { background: none; color: inherit; padding: 0; border: none; }
+.fo code {
+  font-family: var(--mono); font-size: 0.82em; color: var(--warm);
+  background: var(--w-glow); padding: 2px 5px; border-radius: 3px;
+  border: 1px solid rgba(196,138,106,0.12);
+}
+
+/* ── Separator ── */
+.fo-sep {
+  display: flex; align-items: center; justify-content: center;
+  padding: 6px 44px; color: var(--rose); font-size: 0.55rem;
+  letter-spacing: 0.4em; opacity: 0.4;
+}
+.fo-sep::before, .fo-sep::after {
+  content: ''; flex: 1; height: 1px;
+  background: linear-gradient(90deg, transparent, var(--edge), transparent);
+}
+.fo-sep::before { margin-right: 14px; }
+.fo-sep::after { margin-left: 14px; }
+
+/* ── Section divider ── */
+.fo-div {
+  height: 1px; margin: 0 44px;
+  background: linear-gradient(90deg, transparent, var(--edge), transparent);
+}
+
+/* ── Mobile ── */
+@media (max-width: 640px) {
+  .fo-hero img { height: 200px; }
+  .fo-name { font-size: 1.9rem; }
+  .fo-ident { padding: 70px 24px 24px; }
+  .fo-shead { padding: 20px 24px 0; }
+  .fo-sbody { padding: 0 24px 32px; }
+  .fo-grid { grid-template-columns: 1fr; }
+  .fo-metrics { grid-template-columns: repeat(2, 1fr); }
+  .fo-row { grid-template-columns: 1fr; gap: 2px; }
+  .fo-k::after { content: ''; }
+  .fo-sep, .fo-div { margin-left: 24px; margin-right: 24px; padding-left: 24px; padding-right: 24px; }
+}
+</style>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0">
+<title>KomdigiITS-8B-DFK-MergedClassification</title>
+</head>
+<body>
+<div class="fo">
+
+<div class="fo-hero">
+<img src="dfk_hero_banner.png" alt="image">
+<div class="fo-ident">
+<h1 class="fo-name">KomdigiITS-8B-DFK<br>Merged Classification</h1>
+<span class="fo-tagline">Ministral-3-8B &middot; SLERP Merge &middot; Multimodal + Text</span>
+<div class="fo-badge">SLERP &middot; 0.30 multimodal &middot; 0.70 text</div>
+</div>
+</div>
+
+<div class="fo-sep">&#10038;</div>
+
+<!-- ─── 01 · Overview ─── -->
+<div class="fo-section">
+<div class="fo-shead">
+<span class="fo-snum">01</span>
+<span class="fo-stitle">Overview</span>
+</div>
+<div class="fo-sbody">
+<p>A <strong>SLERP-merged</strong> full model combining two specialized LoRA adapters into a single unified checkpoint. The merge blends the <a href="https://huggingface.co/aitf-komdigi/KomdigiITS-8B-DFK-MultimodalClassification">8B Multimodal Multimodal classifier</a> with the <a href="https://huggingface.co/aitf-komdigi/KomdigiITS-8B-DFK-TextClassification">text-only DFK classifier</a>, both built on <a href="https://huggingface.co/aitf-komdigi/KomdigiITS-8B-DFK-CPT">KomdigiITS-8B-DFK-CPT</a> (Ministral-3-8B-Base-2512).</p>
+<p>The result is a model that operates in <strong>two modes</strong>: image-based multimodal classification and text-only classification &mdash; strong performance on both tasks from a single set of weights.</p>
+<div class="fo-note">
+<strong>&#10038; Note:</strong> Best SLERP blend from a parameter sweep (<code>w=0.30</code> multimodal, <code>w=0.70</code> text). Parent adapters were merged into base model weights, producing a standalone model with no adapter overhead.
+</div>
+</div>
+</div>
+
+<div class="fo-div"></div>
+
+<!-- ─── 02 · Model Details ─── -->
+<div class="fo-section">
+<div class="fo-shead">
+<span class="fo-snum">02</span>
+<span class="fo-stitle">Model Details</span>
+</div>
+<div class="fo-sbody">
+<div class="fo-grid">
+<div class="fo-card">
+<div class="fo-chead">Identity</div>
+<div class="fo-row"><span class="fo-k">Developed</span><span class="fo-v">DFK Tim 1 & Tim 3 ITS</span></div>
+<div class="fo-row"><span class="fo-k">Type</span><span class="fo-v">Merged model (SLERP)</span></div>
+<div class="fo-row"><span class="fo-k">Language</span><span class="fo-v">Indonesian</span></div>
+<div class="fo-row"><span class="fo-k">Modes</span><span class="fo-v">Multimodal + Text-only</span></div>
+</div>
+<div class="fo-card fo-card--sage">
+<div class="fo-chead">Architecture</div>
+<div class="fo-row"><span class="fo-k">Base</span><span class="fo-v"><a href="https://huggingface.co/aitf-komdigi/KomdigiITS-8B-DFK-CPT">KomdigiITS-8B-DFK-CPT</a></span></div>
+<div class="fo-row"><span class="fo-k">Arch</span><span class="fo-v">Mistral3ForConditionalGeneration</span></div>
+<div class="fo-row"><span class="fo-k">Params</span><span class="fo-v">8B (full merged weights)</span></div>
+<div class="fo-row"><span class="fo-k">Precision</span><span class="fo-v">float16</span></div>
+</div>
+</div>
+<h3 class="fo-sub">Parent Models</h3>
+<div class="fo-grid">
+<div class="fo-card">
+<div class="fo-chead">Multimodal Parent &middot; w=0.30</div>
+<div class="fo-row"><span class="fo-k">Model</span><span class="fo-v"><a href="https://huggingface.co/aitf-komdigi/KomdigiITS-8B-DFK-MultimodalClassification">8B-DFK-MultimodalClassification</a></span></div>
+<div class="fo-row"><span class="fo-k">Task</span><span class="fo-v">Multimodal &mdash; image + text</span></div>
+<div class="fo-row"><span class="fo-k">Dataset</span><span class="fo-v"><code>dfk_vlm_dataset_v3</code></span></div>
+</div>
+<div class="fo-card fo-card--sage">
+<div class="fo-chead">Text Parent &middot; w=0.70</div>
+<div class="fo-row"><span class="fo-k">Model</span><span class="fo-v"><a href="https://huggingface.co/aitf-komdigi/KomdigiITS-8B-DFK-TextClassification">8B-DFK-TextClassification</a></span></div>
+<div class="fo-row"><span class="fo-k">Task</span><span class="fo-v">Text-only DFK classification</span></div>
+<div class="fo-row"><span class="fo-k">Dataset</span><span class="fo-v"><code>dfk_text_dataset</code></span></div>
+</div>
+</div>
+</div>
+</div>
+
+<div class="fo-div"></div>
+
+<!-- ─── 03 · Uses ─── -->
+<div class="fo-section">
+<div class="fo-shead">
+<span class="fo-snum">03</span>
+<span class="fo-stitle">Uses</span>
+</div>
+<div class="fo-sbody">
+<h3 class="fo-sub">Direct Use</h3>
+<div class="fo-card fo-card--muted" style="margin-bottom:14px;">
+<div class="fo-row"><span class="fo-v">This model supports <strong>two input modes</strong> from a single checkpoint:</span></div>
+</div>
+<div class="fo-grid">
+<div class="fo-card">
+<div class="fo-chead">Mode 1 &middot; Multimodal</div>
+<div class="fo-row"><span class="fo-v">Image-based content moderation. Given a social media screenshot with contextual metadata, classifies into 4 labels: <code>netral</code>, <code>disinformasi</code>, <code>fitnah</code>, or <code>ujaran kebencian</code>.</span></div>
+</div>
+<div class="fo-card fo-card--sage">
+<div class="fo-chead">Mode 2 &middot; Text-Only</div>
+<div class="fo-row"><span class="fo-v">Text-based DFK detection using article references. Classifies into 5 labels: <code>Fakta</code>, <code>Disinformasi</code>, <code>Fitnah</code>, <code>Ujaran Kebencian</code>, or <code>Non-DFK</code>.</span></div>
+</div>
+</div>
+<h3 class="fo-sub">Out-of-Scope Use</h3>
+<div class="fo-card fo-card--warn">
+<div class="fo-row"><span class="fo-v">Not intended for general-purpose vision-language or text generation tasks. Specialized for the DFK  detection pipeline &mdash; should not be used for content moderation in other languages or domains without further fine-tuning.</span></div>
+</div>
+</div>
+</div>
+
+<div class="fo-div"></div>
+
+<!-- ─── 04 · Evaluation ─── -->
+<div class="fo-section">
+<div class="fo-shead">
+<span class="fo-snum">04</span>
+<span class="fo-stitle">Evaluation</span>
+</div>
+<div class="fo-sbody">
+<p>Evaluated on held-out validation splits using greedy decoding (<code>temperature=0.0</code>) and BERTScore (<code>bert-base-multilingual-cased</code>).</p>
+
+<h3 class="fo-sub">Multimodal Task (Image + Text)</h3>
+<div class="fo-metrics">
+<div class="fo-metric fo-metric--sage">
+<div class="fo-mval">88.5</div>
+<div class="fo-mlbl">Accuracy</div>
+</div>
+<div class="fo-metric">
+<div class="fo-mval">89.4</div>
+<div class="fo-mlbl">F1 Weighted</div>
+</div>
+<div class="fo-metric">
+<div class="fo-mval">77.3</div>
+<div class="fo-mlbl">BERTScore F1</div>
+</div>
+<div class="fo-metric">
+<div class="fo-mval">31.6</div>
+<div class="fo-mlbl">ROUGE-L F1</div>
+</div>
+</div>
+
+<h3 class="fo-sub">Text-Only Task</h3>
+<div class="fo-metrics">
+<div class="fo-metric fo-metric--sage">
+<div class="fo-mval">91.0</div>
+<div class="fo-mlbl">Accuracy</div>
+</div>
+<div class="fo-metric">
+<div class="fo-mval">92.9</div>
+<div class="fo-mlbl">F1 Weighted</div>
+</div>
+<div class="fo-metric">
+<div class="fo-mval">77.6</div>
+<div class="fo-mlbl">BERTScore F1</div>
+</div>
+<div class="fo-metric">
+<div class="fo-mval">31.5</div>
+<div class="fo-mlbl">ROUGE-L F1</div>
+</div>
+</div>
+
+<details>
+<summary>Parent Model Comparison</summary>
+<div class="fo-drop">
+<p>The merge trades a small amount of Multimodal accuracy for a <strong>massive improvement</strong> in text-only performance &mdash; turning a Multimodal-only model into a genuinely dual-mode classifier.</p>
+<table class="fo-cmp">
+<thead>
+<tr>
+<th>Model</th>
+<th>Multimodal Acc</th>
+<th>Multimodal F1w</th>
+<th>Multimodal BERT</th>
+<th>Text Acc</th>
+<th>Text F1w</th>
+<th>Text BERT</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td>Multimodal</td>
+<td class="fo-cmp-warm">92.5</td>
+<td class="fo-cmp-warm">92.3</td>
+<td class="fo-cmp-warm">80.0</td>
+<td class="fo-cmp-dim">77.5</td>
+<td class="fo-cmp-dim">70.8</td>
+<td class="fo-cmp-dim">73.1</td>
+</tr>
+<tr>
+<td>Text Adapter</td>
+<td class="fo-cmp-dim">1.5</td>
+<td class="fo-cmp-dim">2.8</td>
+<td class="fo-cmp-dim">69.6</td>
+<td class="fo-cmp-warm">84.0</td>
+<td class="fo-cmp-warm">89.0</td>
+<td class="fo-cmp-warm">80.7</td>
+</tr>
+<tr class="fo-cmp-row-merge">
+<td><strong>SLERP Merge</strong></td>
+<td class="fo-cmp-sage">88.5</td>
+<td class="fo-cmp-sage">89.4</td>
+<td class="fo-cmp-sage">77.3</td>
+<td class="fo-cmp-sage">91.0</td>
+<td class="fo-cmp-sage">92.9</td>
+<td class="fo-cmp-sage">77.6</td>
+</tr>
+</tbody>
+</table>
+<div class="fo-note fo-note--sage">
+<strong>&#10038; Key takeaway:</strong> The merge <em>surpasses</em> the text adapter's own accuracy (91.0 vs 84.0) while retaining 95.7% of the Multimodal model's classification accuracy.
+</div>
+</div>
+</details>
+</div>
+</div>
+
+<div class="fo-div"></div>
+
+<!-- ─── 05 · Merge Details ─── -->
+<div class="fo-section">
+<div class="fo-shead">
+<span class="fo-snum">05</span>
+<span class="fo-stitle">Merge Details</span>
+</div>
+<div class="fo-sbody">
+<h3 class="fo-sub">Method</h3>
+<div class="fo-card" style="margin-bottom:14px;">
+<div class="fo-row"><span class="fo-k">Method</span><span class="fo-v">SLERP (Spherical Linear Interpolation)</span></div>
+<div class="fo-row"><span class="fo-k">Weight</span><span class="fo-v">0.30 multimodal / 0.70 text</span></div>
+<div class="fo-row"><span class="fo-k">Selection</span><span class="fo-v">Best blend from WS3 sweep</span></div>
+<div class="fo-row"><span class="fo-k">Output</span><span class="fo-v">Full merged weights (no adapter)</span></div>
+</div>
+<h3 class="fo-sub">Process</h3>
+<div class="fo-card fo-card--muted" style="margin-bottom:14px;">
+<div class="fo-row"><span class="fo-v">Both parent LoRA adapters (Multimodal + text) were first merged into the base model (<code>KomdigiITS-8B-DFK-CPT</code>) to produce two full-weight checkpoints. These were then interpolated via SLERP at various weight ratios, with each blend evaluated on both Multimodal and text-only benchmarks to find the optimal trade-off.</span></div>
+</div>
+<h3 class="fo-sub">Label Classes</h3>
+<div class="fo-grid">
+<div class="fo-card">
+<div class="fo-chead">Multimodal Mode &middot; 4 Classes</div>
+<div class="fo-row"><span class="fo-k">Netral</span><span class="fo-v">Factual / non-DFK &mdash; no violation</span></div>
+<div class="fo-row"><span class="fo-k">Disinfo</span><span class="fo-v">Claims contradicting established facts</span></div>
+<div class="fo-row"><span class="fo-k">Fitnah</span><span class="fo-v">False claims targeting an individual</span></div>
+<div class="fo-row"><span class="fo-k">Ujrn Kbnci</span><span class="fo-v">Hate speech targeting SARA identity</span></div>
+</div>
+<div class="fo-card fo-card--sage">
+<div class="fo-chead">Text Mode &middot; 5 Classes</div>
+<div class="fo-row"><span class="fo-k">Non-DFK</span><span class="fo-v">Content unrelated to DFK categories</span></div>
+<div class="fo-row"><span class="fo-k">Fakta</span><span class="fo-v">Factual content, verified true</span></div>
+<div class="fo-row"><span class="fo-k">Disinfo</span><span class="fo-v">Claims contradicting established facts</span></div>
+<div class="fo-row"><span class="fo-k">Fitnah</span><span class="fo-v">False claims targeting an individual</span></div>
+<div class="fo-row"><span class="fo-k">Ujrn Kbnci</span><span class="fo-v">Hate speech targeting SARA identity</span></div>
+</div>
+</div>
+</div>
+</div>
+
+<div class="fo-div"></div>
+
+<!-- ─── 06 · Input Formats ─── -->
+<div class="fo-section">
+<div class="fo-shead">
+<span class="fo-snum">06</span>
+<span class="fo-stitle">Input Formats</span>
+</div>
+<div class="fo-sbody">
+<p>Both modes use the <code>ministral_3</code> chat template (<code>[INST]</code> / <code>[/INST]</code> delimiters). The default Ministral system prompt is included when no explicit system message is provided.</p>
+
+<details>
+<summary>Multimodal Mode &middot; dfk_vlm_dataset_v3</summary>
+<div class="fo-drop">
+<p>Image-based classification with contextual metadata. Note: the instruction and context fields are <strong>directly concatenated</strong> with no separator.</p>
+<pre><code>&lt;s&gt;[SYSTEM_PROMPT]...default Ministral system prompt...[/SYSTEM_PROMPT][INST]Anda adalah seorang analis konten media sosial ahli. Diberikan tangkapan layar dari sebuah konten, tentukan label kategori pelanggaran dan berikan analisis detail mengenai pelanggaran yang ditemukan.Ringkasan: {ringkasan}
+Klaim: {klaim}
+Fakta: {fakta}[IMG][/INST]Label: {label}
+
+Analisis: {analisis}&lt;/s&gt;</code></pre>
+
+<h3 class="fo-sub">Input Fields</h3>
+<div class="fo-card" style="margin-bottom:14px;">
+<div class="fo-row"><span class="fo-k">Ringkasan</span><span class="fo-v">Content summary. Concatenation of image caption and user-provided text.</span></div>
+<div class="fo-row"><span class="fo-k">Klaim</span><span class="fo-v">Core claim extracted from the content, used as a web search query for fact-checking.</span></div>
+<div class="fo-row"><span class="fo-k">Fakta</span><span class="fo-v">Verification context from web search. Defaults to <code>"Tidak ditemukan sumber yang valid."</code> if none found.</span></div>
+<div class="fo-row"><span class="fo-k">[IMG]</span><span class="fo-v">Screenshot of the social media post being analyzed.</span></div>
+</div>
+<h3 class="fo-sub">Output Fields</h3>
+<div class="fo-card">
+<div class="fo-row"><span class="fo-k">Label</span><span class="fo-v">One of <code>netral</code>, <code>disinformasi</code>, <code>fitnah</code>, or <code>ujaran kebencian</code>.</span></div>
+<div class="fo-row"><span class="fo-k">Analisis</span><span class="fo-v">Free-form Indonesian-language reasoning for the classification.</span></div>
+</div>
+</div>
+</details>
+
+<details class="fo-det--sage">
+<summary>Text-Only Mode &middot; dfk_text_dataset</summary>
+<div class="fo-drop">
+<p>Text-only classification with explicit system prompt and article references. Uses <code>merge_labels=false</code> (5 classes).</p>
+<pre><code>&lt;s&gt;[SYSTEM_PROMPT]Anda adalah sistem deteksi konten DFK berbasis artikel rujukan. Tugas Anda adalah membandingkan klaim dengan artikel rujukan, lalu mengklasifikasikan teks ke dalam salah satu label: Fakta, Disinformasi, Fitnah, Ujaran Kebencian, atau Non-DFK. Jawab dengan format: Label: **NamaLabel.** penjelasan: ...[/SYSTEM_PROMPT][INST]{klaim}
+
+Artikel Rujukan: {fakta}[/INST]Label: **{label}.** penjelasan: {analisis}&lt;/s&gt;</code></pre>
+
+<h3 class="fo-sub">Input Fields</h3>
+<div class="fo-card" style="margin-bottom:14px;">
+<div class="fo-row"><span class="fo-k">Klaim</span><span class="fo-v">The claim text to be verified, from the <code>input</code> column (before <code>Artikel Rujukan:</code>).</span></div>
+<div class="fo-row"><span class="fo-k">Fakta</span><span class="fo-v">Reference articles for fact-checking, from the <code>input</code> column (after <code>Artikel Rujukan:</code>).</span></div>
+</div>
+<h3 class="fo-sub">Output Fields</h3>
+<div class="fo-card">
+<div class="fo-row"><span class="fo-k">Label</span><span class="fo-v">One of <code>Fakta</code>, <code>Disinformasi</code>, <code>Fitnah</code>, <code>Ujaran Kebencian</code>, or <code>Non-DFK</code>.</span></div>
+<div class="fo-row"><span class="fo-k">Penjelasan</span><span class="fo-v">Indonesian-language explanation for the classification decision.</span></div>
+</div>
+</div>
+</details>
+</div>
+</div>
+
+<div class="fo-div"></div>
+
+<!-- ─── 07 · Model Sources ─── -->
+<div class="fo-section">
+<div class="fo-shead">
+<span class="fo-snum">07</span>
+<span class="fo-stitle">Model Sources</span>
+</div>
+<div class="fo-sbody">
+<div class="fo-card fo-card--muted">
+<div class="fo-row"><span class="fo-k">Framework</span><span class="fo-v"><a href="https://github.com/aitf-its-tim3-dfk/SITA">SITA</a></span></div>
+<div class="fo-row"><span class="fo-k">Base model</span><span class="fo-v"><a href="https://huggingface.co/aitf-komdigi/KomdigiITS-8B-DFK-CPT">aitf-komdigi/KomdigiITS-8B-DFK-CPT</a></span></div>
+<div class="fo-row"><span class="fo-k">Multimodal parent</span><span class="fo-v"><a href="https://huggingface.co/aitf-komdigi/KomdigiITS-8B-DFK-MultimodalClassification">KomdigiITS-8B-DFK-MultimodalClassification</a></span></div>
+<div class="fo-row"><span class="fo-k">Text parent</span><span class="fo-v"><a href="https://huggingface.co/aitf-komdigi/KomdigiITS-8B-DFK-TextClassification">KomdigiITS-8B-DFK-TextClassification</a></span></div>
+</div>
+</div>
+</div>
+
+<div class="fo-div"></div>
+
+<!-- ─── 08 · Framework Versions ─── -->
+<div class="fo-section">
+<div class="fo-shead">
+<span class="fo-snum">08</span>
+<span class="fo-stitle">Framework Versions</span>
+</div>
+<div class="fo-sbody">
+<div class="fo-card fo-card--muted">
+<div class="fo-row"><span class="fo-k">Transformers</span><span class="fo-v">5.5.0</span></div>
+<div class="fo-row"><span class="fo-k">PyTorch</span><span class="fo-v">2.11.0+cu128</span></div>
+<div class="fo-row"><span class="fo-k">Unsloth</span><span class="fo-v">2026.5.5</span></div>
+</div>
+</div>
+</div>
+
+</div>
+</body>
+</html>

chat_template.jinja

@@ -0,0 +1,121 @@
+{#- Unsloth template fixes #}
+{#- Default system message if no system prompt is passed. #}
+{%- set default_system_message = 'You are Ministral-3-8B-Instruct-2512, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYou power an AI assistant called Le Chat.\nYour knowledge base was last updated on 2023-10-01.\nThe current date is {today}.\n\nWhen you\'re not sure about some information or when the user\'s request requires up-to-date or specific data, you must use the available tools to fetch the information. Do not hesitate to use tools whenever they can provide a more accurate or complete response. If no relevant tools are available, then clearly state that you don\'t have the information and avoid making up anything.\nIf the user\'s question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. "What are some good restaurants around me?" => "Where are you?" or "When is the next flight to Tokyo" => "Where do you travel from?").\nYou are always very attentive to dates, in particular you try to resolve dates (e.g. "yesterday" is {yesterday}) and when asked about information at specific dates, you discard information that is at another date.\nYou follow these instructions in all languages, and always respond to the user in the language they use or request.\nNext sections describe the capabilities that you have.\n\n# WEB BROWSING INSTRUCTIONS\n\nYou cannot perform any web search or access internet to open URLs, links etc. If it seems like the user is expecting you to do so, you clarify the situation and ask the user to copy paste the text directly in the chat.\n\n# MULTI-MODAL INSTRUCTIONS\n\nYou have the ability to read images, but you cannot generate images. You also cannot transcribe audio files or videos.\nYou cannot read nor transcribe audio files or videos.\n\n# TOOL CALLING INSTRUCTIONS\n\nYou may have access to tools that you can use to fetch information or perform actions. You must use these tools in the following situations:\n\n1. When the request requires up-to-date information.\n2. When the request requires specific data that you do not have in your knowledge base.\n3. When the request involves actions that you cannot perform without tools.\n\nAlways prioritize using tools to provide the most accurate and helpful response. If tools are not available, inform the user that you cannot perform the requested action at the moment.' %}
+
+{#- Begin of sequence token. #}
+{{- bos_token }}
+
+{#- Handle system prompt if it exists. #}
+{#- System prompt supports text content or text chunks. #}
+{%- if messages[0]['role'] == 'system' %}
+    {{- '[SYSTEM_PROMPT]' -}}
+    {%- if messages[0]['content'] is string %}
+        {{- messages[0]['content'] -}}
+    {%- else %}        
+        {%- for block in messages[0]['content'] %}
+            {%- if block['type'] == 'text' %}
+                {{- block['text'] }}
+            {%- else %}
+                {{- raise_exception('Only text chunks are supported in system message contents.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+    {{- '[/SYSTEM_PROMPT]' -}}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+    {%- if default_system_message != '' %}
+        {{- '[SYSTEM_PROMPT]' + default_system_message + '[/SYSTEM_PROMPT]' }}
+    {%- endif %}
+{%- endif %}
+
+
+{#- Tools definition #}
+{%- set tools_definition = '' %}
+{%- set has_tools = false %}
+{%- if tools is defined and tools is not none and tools|length > 0 %}
+    {%- set has_tools = true %}
+    {%- set tools_definition = '[AVAILABLE_TOOLS]' + (tools| tojson) + '[/AVAILABLE_TOOLS]' %}
+    {{- tools_definition }}
+{%- endif %}
+
+{#- Checks for alternating user/assistant messages. #}
+{%- set ns = namespace(index=0) %}
+{%- for message in loop_messages %}
+    {%- if message.role == 'user' or (message.role == 'assistant' and (message.tool_calls is not defined or message.tool_calls is none or message.tool_calls | length == 0)) %}
+        {%- if (message['role'] == 'user') != (ns.index % 2 == 0) %}
+            {{- raise_exception('After the optional system message, conversation roles must alternate user and assistant roles except for tool calls and results.') }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{#- Handle conversation messages. #}
+{%- for message in loop_messages %}
+
+    {#- User messages supports text content or text and image chunks. #}
+    {%- if message['role'] == 'user' %}
+        {%- if message['content'] is string %}
+            {{- '[INST]' + message['content'] + '[/INST]' }}
+        {%- elif message['content'] | length > 0 %}
+            {{- '[INST]' }}
+            {%- if message['content'] | length == 2 %}
+                {%- set blocks = message['content'] | sort(attribute='type') %}
+            {%- else %}
+                {%- set blocks = message['content'] %}
+            {%- endif %}
+            {%- for block in blocks %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- elif block['type'] in ['image', 'image_url'] %}
+                    {{- '[IMG]' }}
+                {%- else %}
+                    {{- raise_exception('Only text, image and image_url chunks are supported in user message content.') }}
+                {%- endif %}
+            {%- endfor %}
+            {{- '[/INST]' }}
+        {%- else %}
+            {{- raise_exception('User message must have a string or a list of chunks in content') }}
+        {%- endif %}
+
+    {#- Assistant messages supports text content or text and image chunks. #}
+    {%- elif message['role'] == 'assistant' %}
+
+        {%- if message['content'] is string %}
+            {{- message['content'] }}
+        {%- elif message['content'] is iterable and message['content'] | length > 0 %}
+            {%- for block in message['content'] %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- else %}
+                    {{- raise_exception('Only text chunks are supported in assistant message contents.') }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        
+        {%- if message['tool_calls'] is defined and message['tool_calls'] is not none and message['tool_calls']|length > 0 %}
+            {%- for tool in message['tool_calls'] %}
+                {%- set arguments = tool['function']['arguments'] %}
+                {%- if arguments is not string %}
+                    {%- set arguments = arguments|tojson|safe %}
+                {%- elif arguments == '' %}
+                    {%- set arguments = '{}' %}
+                {%- endif %}
+                {{- '[TOOL_CALLS]' + tool['function']['name'] + '[ARGS]' + arguments }}
+            {%- endfor %}
+        {%- endif %}
+
+        {#- End of sequence token for each assistant messages. #}
+        {{- eos_token }}
+
+    {#- Tool messages only supports text content. #}
+    {%- elif message['role'] == 'tool' %}
+        {{- '[TOOL_RESULTS]' + message['content']|string + '[/TOOL_RESULTS]' }}
+
+    {#- Raise exception for unsupported roles. #}
+    {%- else %}
+        {{- raise_exception('Only user, assistant and tool roles are supported, got ' + message['role']) }}
+    {%- endif %}
+{%- endfor %}
+
+{#- Copyright 2025-present Unsloth. Apache 2.0 License. #}

metrics.json

@@ -0,0 +1,34 @@
+{
+  "models": {
+    "DFK-3_multimodal": {
+      "vlm_gen/cls_accuracy": 0.925,
+      "vlm_gen/cls_f1_weighted": 0.9231573444047207,
+      "vlm_gen/bertscore_f1": 0.8003071546554565,
+      "vlm_gen/rouge_l_f1": 0.387058103281244,
+      "text_gen/cls_accuracy": 0.775,
+      "text_gen/cls_f1_weighted": 0.7083681876531683,
+      "text_gen/bertscore_f1": 0.730573296546936,
+      "text_gen/rouge_l_f1": 0.18964804860834042
+    },
+    "DFK-1_text": {
+      "vlm_gen/cls_accuracy": 0.015,
+      "vlm_gen/cls_f1_weighted": 0.028181818181818183,
+      "vlm_gen/bertscore_f1": 0.6958135962486267,
+      "vlm_gen/rouge_l_f1": 0.16208120267774412,
+      "text_gen/cls_accuracy": 0.84,
+      "text_gen/cls_f1_weighted": 0.889809384164223,
+      "text_gen/bertscore_f1": 0.8070414662361145,
+      "text_gen/rouge_l_f1": 0.4163341020470059
+    },
+    "Best_SLERP_Blend_w_0.30_mm_0.70_text": {
+      "vlm_gen/cls_accuracy": 0.885,
+      "vlm_gen/cls_f1_weighted": 0.8943747841713945,
+      "vlm_gen/bertscore_f1": 0.773254930973053,
+      "vlm_gen/rouge_l_f1": 0.3163897617151505,
+      "text_gen/cls_accuracy": 0.91,
+      "text_gen/cls_f1_weighted": 0.9288329276209023,
+      "text_gen/bertscore_f1": 0.7756227254867554,
+      "text_gen/rouge_l_f1": 0.3150810618299241
+    }
+  }
+}