Upload all models and assets for ary (latest)

README.md

@@ -33,733 +33,198 @@ dataset_info:
 metrics:
   - name: best_compression_ratio
     type: compression
-    value: 4.171
+    value: 4.172
   - name: best_isotropy
     type: isotropy
-    value: 0.8284
+    value: 0.8215
+  - name: best_alignment_r10
+    type: alignment
+    value: 0.2420
   - name: vocabulary_size
     type: vocab
-    value: 0
-generated: 2026-01-03
+    value: 79667
+generated: 2026-03-02
 ---
 
-# Moroccan Arabic - Wikilangs Models
-## Comprehensive Research Report & Full Ablation Study
+# Moroccan Arabic — Wikilangs Models
 
-This repository contains NLP models trained and evaluated by Wikilangs, specifically on **Moroccan Arabic** Wikipedia data.
-We analyze tokenizers, n-gram models, Markov chains, vocabulary statistics, and word embeddings.
+Open-source tokenizers, n-gram & Markov language models, vocabulary stats, and word embeddings trained on **Moroccan Arabic** Wikipedia by [Wikilangs](https://wikilangs.org).
 
-## 📋 Repository Contents
+🌐 [Language Page](https://wikilangs.org/languages/ary/) · 🎮 [Playground](https://wikilangs.org/playground/?lang=ary) · 📊 [Full Research Report](RESEARCH_REPORT.md)
 
-### Models & Assets
+## Language Samples
 
-- Tokenizers (8k, 16k, 32k, 64k)
-- N-gram models (2, 3, 4, 5-gram)
-- Markov chains (context of 1, 2, 3, 4 and 5)
-- Subword N-gram and Markov chains
-- Embeddings in various sizes and dimensions (aligned and unaligned)
-- Language Vocabulary
-- Language Statistics
+Example sentences drawn from the Moroccan Arabic Wikipedia corpus:
 
-![Performance Dashboard](visualizations/performance_dashboard.png)
+> آيت ميلك جماعة ترابية قروية كاينة في إقليم اشتوكة آيت باها، جهة سوس ماسة، ساكنين فيها نسمة، على حسب الإحصاء العام ويب
 
-### Analysis and Evaluation
+> أورو هي لفلوس لي كاتخدًم بزاف ديال الدول ديال الاتحاد الأوروپي. هاد الدول تافقو يخدًمو الأورو مبعد المعاهدة ديال ماستريخت عام شوف حتى الاتحاد الأوروپي مصادر
 
-- [1. Tokenizer Evaluation](#1-tokenizer-evaluation)
-- [2. N-gram Model Evaluation](#2-n-gram-model-evaluation)
-- [3. Markov Chain Evaluation](#3-markov-chain-evaluation)
-- [4. Vocabulary Analysis](#4-vocabulary-analysis)
-- [5. Word Embeddings Evaluation](#5-word-embeddings-evaluation)
-- [6. Morphological Analysis (Experimental)](#6--morphological-analysis-experimental)
-- [7. Summary & Recommendations](#7-summary--recommendations)
-- [Metrics Glossary](#appendix-metrics-glossary--interpretation-guide)
-- [Visualizations Index](#visualizations-index)
+> إيلبا (ب ، إيصولا د إيلبا) هي واحد الجزيرة تابعة للطاليان و تيسكن فيها تقريبا 30.000 واحد. جات ف البحر البيض المتوسط مابين طوسكانيا و كورسيكا. مصادر ف الطاليان ݣزيرة
 
----
-## 1. Tokenizer Evaluation
+> حرب كردستان لعراق هي واحد الحرب ف كردستان لعراق سالات بالربح ديال لعراق. بدات ف عام و سالات ف و ربح فيها لعراق مين كان حاكمو حزب لبعث. مصادر
 
-![Tokenizer Compression](visualizations/tokenizer_compression.png)
+> الدارجة التطوانية هي الدارجة لي كيهضرو الناس د المدينة د تطوان و النواحي ديالا، و عندها تأثيرات من العربية د الأندلس و اللهجة الجبلية لي قريبا لها. مصادر د داريجة
 
-![Tokenizer Fertility](visualizations/tokenizer_fertility.png)
+## Quick Start
 
-![Tokenizer OOV](visualizations/tokenizer_oov.png)
+### Load the Tokenizer
 
-![Total Tokens](visualizations/tokenizer_total_tokens.png)
+```python
+import sentencepiece as spm
 
-### Results
+sp = spm.SentencePieceProcessor()
+sp.Load("ary_tokenizer_32k.model")
 
-| Vocab Size | Compression | Avg Token Len | UNK Rate | Total Tokens |
-|------------|-------------|---------------|----------|--------------|
-| **8k** | 3.480x | 3.48 | 0.0910% | 300,099 |
-| **16k** | 3.753x | 3.76 | 0.0981% | 278,271 |
-| **32k** | 3.983x | 3.99 | 0.1041% | 262,209 |
-| **64k** | 4.171x 🏆 | 4.18 | 0.1090% | 250,397 |
+text = "قريش هيا قبيلة ؤلا أجموع قبلي لي، علا حساب لمصادر لإسلامية، كانت ف مكة ؤ كاينتام"
+tokens = sp.EncodeAsPieces(text)
+ids    = sp.EncodeAsIds(text)
 
-### Tokenization Examples
+print(tokens)  # subword pieces
+print(ids)     # integer ids
 
-Below are sample sentences tokenized with each vocabulary size:
+# Decode back
+print(sp.DecodeIds(ids))
+```
 
-**Sample 1:** `هادي صفحة د التوضيح، كلمة بركان يمكن يكونو عندها هاد لمعاني: بْرْكان: مدينة مغري...`
+<details>
+<summary><b>Tokenization examples (click to expand)</b></summary>
+
+**Sample 1:** `قريش هيا قبيلة ؤلا أجموع قبلي لي، عل�� حساب لمصادر لإسلامية، كانت ف مكة ؤ كاينتام…`
 
 | Vocab | Tokens | Count |
 |-------|--------|-------|
-| 8k | `▁هادي ▁صفحة ▁د ▁التوضيح ، ▁كلمة ▁بركان ▁يمكن ▁يكونو ▁عندها ... (+23 more)` | 33 |
-| 16k | `▁هادي ▁صفحة ▁د ▁التوضيح ، ▁كلمة ▁بركان ▁يمكن ▁يكونو ▁عندها ... (+21 more)` | 31 |
-| 32k | `▁هادي ▁صفحة ▁د ▁التوضيح ، ▁كلمة ▁بركان ▁يمكن ▁يكونو ▁عندها ... (+19 more)` | 29 |
-| 64k | `▁هادي ▁صفحة ▁د ▁التوضيح ، ▁كلمة ▁بركان ▁يمكن ▁يكونو ▁عندها ... (+18 more)` | 28 |
+| 8k | `▁ق ريش ▁هيا ▁قبيلة ▁ؤلا ▁أج موع ▁ق بلي ▁لي … (+19 more)` | 29 |
+| 16k | `▁قريش ▁هيا ▁قبيلة ▁ؤلا ▁أج موع ▁ق بلي ▁لي ، … (+16 more)` | 26 |
+| 32k | `▁قريش ▁هيا ▁قبيلة ▁ؤلا ▁أجموع ▁ق بلي ▁لي ، ▁علا … (+15 more)` | 25 |
+| 64k | `▁قريش ▁هيا ▁قبيلة ▁ؤلا ▁أجموع ▁قبلي ▁لي ، ▁علا ▁حساب … (+14 more)` | 24 |
 
-**Sample 2:** `لْفزضاض ؤلا أفزضاض (سمية لعلمية Microcosmus sabatieri) حيوان لاسنسولي كيعيش ف لب...`
+**Sample 2:** `آيت ميلك جماعة ترابية قروية كاينة في إقليم اشتوكة آيت باها، جهة سوس ماسة، ساكنين…`
 
 | Vocab | Tokens | Count |
 |-------|--------|-------|
-| 8k | `▁لْ ف ز ضاض ▁ؤلا ▁أف ز ضاض ▁( سمية ... (+31 more)` | 41 |
-| 16k | `▁لْ ف ز ضاض ▁ؤلا ▁أف ز ضاض ▁( سمية ... (+28 more)` | 38 |
-| 32k | `▁لْف ز ضاض ▁ؤلا ▁أف ز ضاض ▁( سمية ▁لعلمية ... (+25 more)` | 35 |
-| 64k | `▁لْف زضاض ▁ؤلا ▁أف زضاض ▁( سمية ▁لعلمية ▁microcos mus ... (+17 more)` | 27 |
+| 8k | `▁آيت ▁ميل ك ▁جماعة ▁ترابية ▁قروية ▁كاينة ▁في ▁إقليم ▁اشتوكة … (+16 more)` | 26 |
+| 16k | `▁آيت ▁ميل ك ▁جماعة ▁ترابية ▁قروية ▁كاينة ▁في ▁إقليم ▁اشتوكة … (+16 more)` | 26 |
+| 32k | `▁آيت ▁ميل ك ▁جماعة ▁ترابية ▁قروية ▁كاينة ▁في ▁إقليم ▁اشتوكة … (+16 more)` | 26 |
+| 64k | `▁آيت ▁ميلك ▁جماعة ▁ترابية ▁قروية ▁كاينة ▁في ▁إقليم ▁اشتوكة ▁آيت … (+15 more)` | 25 |
 
-**Sample 3:** `نيلز أبراهام لانݣليت (مزيود ف 9 يوليوز - مات ف 30 مارس هوّا عالم د شّيمي سويدي. ...`
+**Sample 3:** `خديجة بنت علي بن أبي طالب، هي بنت علي بن أبي طالب. مصادر د نسا`
 
 | Vocab | Tokens | Count |
 |-------|--------|-------|
-| 8k | `▁نيل ز ▁أب راهام ▁ل انݣ ليت ▁( مزيود ▁ف ... (+19 more)` | 29 |
-| 16k | `▁نيل ز ▁أبراهام ▁ل انݣ ليت ▁( مزيود ▁ف ▁ ... (+16 more)` | 26 |
-| 32k | `▁نيلز ▁أبراهام ▁لانݣ ليت ▁( مزيود ▁ف ▁ 9 ▁يوليوز ... (+14 more)` | 24 |
-| 64k | `▁نيلز ▁أبراهام ▁لانݣليت ▁( مزيود ▁ف ▁ 9 ▁يوليوز ▁- ... (+13 more)` | 23 |
-
-
-### Key Findings
-
-- **Best Compression:** 64k achieves 4.171x compression
-- **Lowest UNK Rate:** 8k with 0.0910% unknown tokens
-- **Trade-off:** Larger vocabularies improve compression but increase model size
-- **Recommendation:** 32k vocabulary provides optimal balance for production use
-
----
-## 2. N-gram Model Evaluation
-
-![N-gram Perplexity](visualizations/ngram_perplexity.png)
-
-![N-gram Unique](visualizations/ngram_unique.png)
-
-![N-gram Coverage](visualizations/ngram_coverage.png)
-
-### Results
-
-| N-gram | Variant | Perplexity | Entropy | Unique N-grams | Top-100 Coverage | Top-1000 Coverage |
-|--------|---------|------------|---------|----------------|------------------|-------------------|
-| **2-gram** | Word | 7,228 | 12.82 | 39,512 | 23.0% | 50.8% |
-| **2-gram** | Subword | 424 🏆 | 8.73 | 5,903 | 58.0% | 96.4% |
-| **3-gram** | Word | 5,655 | 12.47 | 43,555 | 27.5% | 57.1% |
-| **3-gram** | Subword | 3,784 | 11.89 | 44,651 | 23.1% | 60.7% |
-| **4-gram** | Word | 7,985 | 12.96 | 70,559 | 27.5% | 53.6% |
-| **4-gram** | Subword | 20,064 | 14.29 | 220,807 | 12.0% | 36.0% |
-| **5-gram** | Word | 7,565 | 12.89 | 58,964 | 28.5% | 52.9% |
-| **5-gram** | Subword | 62,379 | 15.93 | 527,725 | 7.3% | 25.0% |
-
-### Top 5 N-grams by Size
-
-**2-grams (Word):**
-
-| Rank | N-gram | Count |
-|------|--------|-------|
-| 1 | `واصلة ل` | 8,540 |
-| 2 | `نسبة د` | 7,170 |
-| 3 | `ف لمغريب` | 6,305 |
-| 4 | `ف إقليم` | 6,018 |
-| 5 | `ف نسبة` | 4,265 |
-
-**3-grams (Word):**
-
-| Rank | N-gram | Count |
-|------|--------|-------|
-| 1 | `ف نسبة د` | 4,264 |
-| 2 | `فيها مصدر و` | 3,236 |
-| 3 | `و نسبة د` | 2,894 |
-| 4 | `مصدر و بايت` | 2,856 |
-| 5 | `اللي خدامين ف` | 2,760 |
-
-**4-grams (Word):**
-
-| Rank | N-gram | Count |
-|------|--------|-------|
-| 1 | `فيها مصدر و بايت` | 2,856 |
-| 2 | `نسبة نّاس اللي خدامين` | 2,705 |
-| 3 | `نّاس اللي خدامين ف` | 2,594 |
-| 4 | `على حساب لإحصاء الرسمي` | 2,501 |
-| 5 | `حساب لإحصاء الرسمي د` | 2,500 |
-
-**5-grams (Word):**
-
-| Rank | N-gram | Count |
-|------|--------|-------|
-| 1 | `نسبة نّاس اللي خدامين ف` | 2,593 |
-| 2 | `ف لمغريب هاد دّوار كينتامي` | 2,500 |
-| 3 | `هاد دّوار كينتامي ل مشيخة` | 2,500 |
-| 4 | `لمغريب هاد دّوار كينتامي ل` | 2,500 |
-| 5 | `حساب لإحصاء الرسمي د عام` | 2,500 |
-
-**2-grams (Subword):**
-
-| Rank | N-gram | Count |
-|------|--------|-------|
-| 1 | `ا ل` | 347,466 |
-| 2 | `_ ل` | 278,371 |
-| 3 | `ة _` | 229,442 |
-| 4 | `_ ا` | 220,960 |
-| 5 | `_ م` | 156,801 |
-
-**3-grams (Subword):**
-
-| Rank | N-gram | Count |
-|------|--------|-------|
-| 1 | `_ ا ل` | 216,048 |
-| 2 | `_ ف _` | 83,146 |
-| 3 | `ا ت _` | 63,800 |
-| 4 | `ي ة _` | 60,271 |
-| 5 | `_ د _` | 59,563 |
-
-**4-grams (Subword):**
-
-| Rank | N-gram | Count |
-|------|--------|-------|
-| 1 | `_ د ي ا` | 47,798 |
-| 2 | `د ي ا ل` | 47,559 |
-| 3 | `ي ا ل _` | 33,039 |
-| 4 | `د _ ا ل` | 32,831 |
-| 5 | `_ م ن _` | 28,909 |
-
-**5-grams (Subword):**
-
-| Rank | N-gram | Count |
-|------|--------|-------|
-| 1 | `_ د ي ا ل` | 47,427 |
-| 2 | `د ي ا ل _` | 32,608 |
-| 3 | `_ ع ل ى _` | 19,473 |
-| 4 | `_ ا ل ل ي` | 18,967 |
-| 5 | `ا ل ل ي _` | 18,744 |
-
-
-### Key Findings
-
-- **Best Perplexity:** 2-gram (subword) with 424
-- **Entropy Trend:** Decreases with larger n-grams (more predictable)
-- **Coverage:** Top-1000 patterns cover ~25% of corpus
-- **Recommendation:** 4-gram or 5-gram for best predictive performance
-
----
-## 3. Markov Chain Evaluation
-
-![Markov Entropy](visualizations/markov_entropy.png)
-
-![Markov Contexts](visualizations/markov_contexts.png)
-
-![Markov Branching](visualizations/markov_branching.png)
-
-### Results
-
-| Context | Variant | Avg Entropy | Perplexity | Branching Factor | Unique Contexts | Predictability |
-|---------|---------|-------------|------------|------------------|-----------------|----------------|
-| **1** | Word | 0.8561 | 1.810 | 5.38 | 178,865 | 14.4% |
-| **1** | Subword | 1.1236 | 2.179 | 8.36 | 2,156 | 0.0% |
-| **2** | Word | 0.2259 | 1.169 | 1.49 | 962,233 | 77.4% |
-| **2** | Subword | 0.8160 | 1.761 | 5.10 | 18,029 | 18.4% |
-| **3** | Word | 0.0618 | 1.044 | 1.10 | 1,431,084 | 93.8% |
-| **3** | Subword | 0.8022 | 1.744 | 4.13 | 91,858 | 19.8% |
-| **4** | Word | 0.0208 🏆 | 1.015 | 1.04 | 1,574,083 | 97.9% |
-| **4** | Subword | 0.6604 | 1.581 | 2.86 | 379,445 | 34.0% |
-
-### Generated Text Samples (Word-based)
-
-Below are text samples generated from each word-based Markov chain model:
-
-**Context Size 1:**
-
-1. `ف لمغريب فيها 5 463 462 461 كم من غير ب شبه منقّر مكررعبد المسيح في`
-2. `و أداب روسيا ف لمغريب ف وقت مابين اللغات الرسمية ديال حيزب لإستقلال تا سينيما ليها`
-3. `د الناس فليبيا اكتشفو أنه يتقتل ولكن بقات كتلعب فالتيران ديال هاد الريحلة معا لمونتاخاب و`
-
-**Context Size 2:**
-
-1. `واصلة ل 98 6 و عدد لفاميلات تزاد ب 81 6 و نسبة د الناس و لمحيط`
-2. `نسبة د الشوماج واصلة ل 21 12 نوطات مصادر ف لمغريب جّبل معروف عند الصامويين حتال ليوم`
-3. `ف لمغريب هاد دّوار كينتامي ل مشيخة سدي حمد الدغوغي لي كتضم 14 د دّواور لعاداد د`
-
-**Context Size 3:**
-
-1. `ف نسبة د التسكويل واصلة ل 91 89 و نسبة د الشوماج واصلة ل 7 6 و لخصوبة`
-2. `فيها مصدر و بايت زادهوم داريجابوت حيين مغاربا د لقرن 21 مغاربا مغاربا فيها مصدر و بايت زادهوم`
-3. `و نسبة د لأمية واصلة ل 53 4 و نسبة د لأمية واصلة ل 92 5 و نسبة`
-
-**Context Size 4:**
-
-1. `نسبة نّاس اللي خدامين ف دّولة ولا لبيطاليين اللي سبق ليهوم خدمو 44 3 نسبة نّاس اللي خدامين ف`
-2. `نّاس اللي خدامين ف لپريڤي ولا لبيطاليين اللي سبق ليهوم مصادر الدار البيضاء سطات قروية ف إقليم سطات ق...`
-3. `على حساب لإحصاء الرسمي د عام إحصائيات إحصائيات عامة عدد السكان ديال أورسفان نقص ب 30 7 و عدد`
-
-
-### Generated Text Samples (Subword-based)
-
-Below are text samples generated from each subword-based Markov chain model:
-
-**Context Size 1:**
-
-1. `_دّرى_لجالب_لتالع`
-2. `اكترن_لعاميلة_ن_`
-3. `لت_پرومدي_و_ماتم`
-
-**Context Size 2:**
-
-1. `الرجل_بين_ماعة_لخ`
-2. `_لكينو_العرفوقعوه`
-3. `ة_27_نت،_خري_د_لج`
-
-**Context Size 3:**
+| 8k | `▁خديجة ▁بنت ▁علي ▁بن ▁أبي ▁طالب ، ▁هي ▁بنت ▁علي … (+7 more)` | 17 |
+| 16k | `▁خديجة ▁بنت ▁علي ▁بن ▁أبي ▁طالب ، ▁هي ▁بنت ▁علي … (+7 more)` | 17 |
+| 32k | `▁خديجة ▁بنت ▁علي ▁بن ▁أبي ▁طالب ، ▁هي ▁بنت ▁علي … (+7 more)` | 17 |
+| 64k | `▁خديجة ▁بنت ▁علي ▁بن ▁أبي ▁طالب ، ▁هي ▁بنت ▁علي … (+7 more)` | 17 |
 
-1. `_الروس_و_هي_ماية_ك`
-2. `_ف_موقريب._الدفايي`
-3. `ات_ف_البالشخصياتول`
+</details>
 
-**Context Size 4:**
+### Load Word Embeddings
 
-1. `_ديالو._ميامينش_و_ت`
-2. `ديال_أسباب_الغرب_6_`
-3. `يال_تعرّض_للحزب_الوه`
+```python
+from gensim.models import KeyedVectors
 
+# Aligned embeddings (cross-lingual, mapped to English vector space)
+wv = KeyedVectors.load("ary_embeddings_128d_aligned.kv")
 
-### Key Findings
-
-- **Best Predictability:** Context-4 (word) with 97.9% predictability
-- **Branching Factor:** Decreases with context size (more deterministic)
-- **Memory Trade-off:** Larger contexts require more storage (379,445 contexts)
-- **Recommendation:** Context-3 or Context-4 for text generation
-
----
-## 4. Vocabulary Analysis
-
-![Zipf's Law](visualizations/zipf_law.png)
-
-![Top Words](visualizations/top20_words.png)
-
-![Coverage Curve](visualizations/vocab_coverage.png)
-
-### Statistics
-
-| Metric | Value |
-|--------|-------|
-| Vocabulary Size | 78,779 |
-| Total Tokens | 2,032,841 |
-| Mean Frequency | 25.80 |
-| Median Frequency | 4 |
-| Frequency Std Dev | 515.92 |
-
-### Most Common Words
-
-| Rank | Word | Frequency |
-|------|------|-----------|
-| 1 | ف | 83,458 |
-| 2 | و | 59,829 |
-| 3 | د | 59,731 |
-| 4 | ديال | 32,565 |
-| 5 | من | 29,236 |
-| 6 | ل | 23,572 |
-| 7 | على | 19,570 |
-| 8 | لي | 18,402 |
-| 9 | اللي | 17,442 |
-| 10 | ب | 17,233 |
-
-### Least Common Words (from vocabulary)
-
-| Rank | Word | Frequency |
-|------|------|-----------|
-| 1 | بوفوار | 2 |
-| 2 | بيتسي | 2 |
-| 3 | وصانعي | 2 |
-| 4 | وأهميتها | 2 |
-| 5 | بورديو | 2 |
-| 6 | بلومر | 2 |
-| 7 | مقترحة | 2 |
-| 8 | anchor | 2 |
-| 9 | بعصبة | 2 |
-| 10 | ماڭي | 2 |
-
-### Zipf's Law Analysis
-
-| Metric | Value |
-|--------|-------|
-| Zipf Coefficient | 1.0213 |
-| R² (Goodness of Fit) | 0.998918 |
-| Adherence Quality | **excellent** |
-
-### Coverage Analysis
-
-| Top N Words | Coverage |
-|-------------|----------|
-| Top 100 | 38.6% |
-| Top 1,000 | 62.9% |
-| Top 5,000 | 77.8% |
-| Top 10,000 | 84.2% |
-
-### Key Findings
-
-- **Zipf Compliance:** R²=0.9989 indicates excellent adherence to Zipf's law
-- **High Frequency Dominance:** Top 100 words cover 38.6% of corpus
-- **Long Tail:** 68,779 words needed for remaining 15.8% coverage
-
----
-## 5. Word Embeddings Evaluation
-
-![Embedding Isotropy](visualizations/embedding_isotropy.png)
-
-![Similarity Matrix](visualizations/embedding_similarity.png)
-
-![t-SNE Words](visualizations/tsne_words.png)
-
-![t-SNE Sentences](visualizations/tsne_sentences.png)
-
-
-### 5.1 Cross-Lingual Alignment
-
-![Alignment Quality](visualizations/embedding_alignment_quality.png)
-
-![Multilingual t-SNE](visualizations/embedding_tsne_multilingual.png)
-
-
-### 5.2 Model Comparison
-
-| Model | Dimension | Isotropy | Semantic Density | Alignment R@1 | Alignment R@10 |
-|-------|-----------|----------|------------------|---------------|----------------|
-| **mono_32d** | 32 | 0.8284 🏆 | 0.3330 | N/A | N/A |
-| **mono_64d** | 64 | 0.8181 | 0.2588 | N/A | N/A |
-| **mono_128d** | 128 | 0.7036 | 0.2093 | N/A | N/A |
-| **aligned_32d** | 32 | 0.8284 | 0.3345 | 0.0180 | 0.1360 |
-| **aligned_64d** | 64 | 0.8181 | 0.2550 | 0.0380 | 0.1760 |
-| **aligned_128d** | 128 | 0.7036 | 0.2072 | 0.0620 | 0.2760 |
+similar = wv.most_similar("word", topn=5)
+for word, score in similar:
+    print(f"  {word}: {score:.3f}")
+```
 
-### Key Findings
+### Load N-gram Model
 
-- **Best Isotropy:** mono_32d with 0.8284 (more uniform distribution)
-- **Semantic Density:** Average pairwise similarity of 0.2663. Lower values indicate better semantic separation.
-- **Alignment Quality:** Aligned models achieve up to 6.2% R@1 in cross-lingual retrieval.
-- **Recommendation:** 128d aligned for best cross-lingual performance
+```python
+import pyarrow.parquet as pq
 
----
-## 6.  Morphological Analysis (Experimental)
-
-This section presents an automated morphological analysis derived from the statistical divergence between word-level and subword-level models. By analyzing where subword predictability spikes and where word-level coverage fails, we can infer linguistic structures without supervised data.
-
-### 6.1 Productivity & Complexity
-
-| Metric | Value | Interpretation | Recommendation |
-|--------|-------|----------------|----------------|
-| Productivity Index | **5.000** | High morphological productivity | Reliable analysis |
-| Idiomaticity Gap | **1.114** | High formulaic/idiomatic content | - |
-
-### 6.2 Affix Inventory (Productive Units)
-
-These are the most productive prefixes and suffixes identified by sampling the vocabulary for global substitutability patterns. A unit is considered an affix if stripping it leaves a valid stem that appears in other contexts.
-
-#### Productive Prefixes
-| Prefix | Examples |
-|--------|----------|
-| `-ال` | الأمني, اللحظة, الفيرمات |
-| `-لم` | لمتعصبين, لمحافض, لمونضامة |
-| `-كا` | كاتدير, كايتحلو, كايقممو |
-
-#### Productive Suffixes
-| Suffix | Examples |
-|--------|----------|
-| `-ة` | سميّة, رقصة, اللحظة |
-| `-ات` | سطراتيجيات, الفيرمات, لحتيفالات |
-| `-ية` | الشرقية, اللاجنسية, ولوسطانية |
-| `-ين` | لمتعصبين, ثنين, لمالحين |
-
-### 6.3 Bound Stems (Lexical Roots)
-
-Bound stems are high-frequency subword units that are semantically cohesive but rarely appear as standalone words. These often correspond to the 'core' of a word that requires inflection or derivation to be valid.
-
-| Stem | Cohesion | Substitutability | Examples |
-|------|----------|------------------|----------|
-| `انية` | 1.80x | 68 contexts | غانية, ثانية, سانية |
-| `اللو` | 1.74x | 61 contexts | اللوه, اللور, اللول |
-| `الات` | 1.71x | 65 contexts | تالات, حالات, صالات |
-| `جماع` | 1.90x | 38 contexts | جماعي, تجماع, إجماع |
-| `النا` | 1.63x | 63 contexts | الناي, النار, الناس |
-| `لمغر` | 1.92x | 30 contexts | لمغرب, لمغربب, للمغرب |
-| `إحصا` | 2.13x | 17 contexts | إحصاء, لإحصا, إحصائي |
-| `مغري` | 2.08x | 18 contexts | مغريب, مغرية, مغريبي |
-| `حصاء` | 2.24x | 14 contexts | إحصاء, لإحصاء, ليحصاء |
-| `دهوم` | 2.14x | 16 contexts | ضدهوم, يردهوم, زادهوم |
-| `قليم` | 2.06x | 17 contexts | فقليم, اقليم, إقليم |
-| `لجوا` | 1.77x | 26 contexts | لجواب, لجواد, الجوا |
-
-### 6.4 Affix Compatibility (Co-occurrence)
-
-This table shows which prefixes and suffixes most frequently co-occur on the same stems, revealing the 'stacking' rules of the language's morphology.
-
-| Prefix | Suffix | Frequency | Examples |
-|--------|--------|-----------|----------|
-| `-ال` | `-ة` | 280 words | الراكوبة, العمدة |
-| `-ال` | `-ات` | 163 words | الشلالات, العبرات |
-| `-ال` | `-ية` | 152 words | الزراعية, الطباشيرية |
-| `-ال` | `-ين` | 76 words | الموحدين, الاثنين |
-| `-لم` | `-ة` | 66 words | لمملكة, لمُحمدية |
-| `-لم` | `-ين` | 45 words | لموناضيلين, لمعتقلين |
-| `-لم` | `-ات` | 25 words | لمونضّامات, لممرات |
-| `-لم` | `-ية` | 21 words | لمُحمدية, لمراكشية |
-| `-كا` | `-ين` | 2 words | كايسين, كاتبين |
-
-### 6.5 Recursive Morpheme Segmentation
-
-Using **Recursive Hierarchical Substitutability**, we decompose complex words into their constituent morphemes. This approach handles nested affixes (e.g., `prefix-prefix-root-suffix`).
-
-| Word | Suggested Split | Confidence | Stem |
-|------|-----------------|------------|------|
-| التوجيهات | **`ال-توجيه-ات`** | 6.0 | `توجيه` |
-| الصومالية | **`ال-صومال-ية`** | 6.0 | `صومال` |
-| الپاكستانية | **`ال-پاكستان-ية`** | 6.0 | `پاكستان` |
-| الدوّازات | **`ال-دوّاز-ات`** | 6.0 | `دوّاز` |
-| الصالونات | **`ال-صالون-ات`** | 6.0 | `صالون` |
-| التعبيرية | **`ال-تعبير-ية`** | 6.0 | `تعبير` |
-| الانقلابية | **`ال-انقلاب-ية`** | 6.0 | `انقلاب` |
-| لمنقارضين | **`لم-نقارض-ين`** | 6.0 | `نقارض` |
-| التقليديين | **`ال-تقليدي-ين`** | 6.0 | `تقليدي` |
-| لمنتاشرين | **`لم-نتاشر-ين`** | 6.0 | `نتاشر` |
-| الماكينات | **`ال-ماكين-ات`** | 6.0 | `ماكين` |
-| البرونزية | **`ال-برونز-ية`** | 6.0 | `برونز` |
-| التكوينية | **`ال-تكوين-ية`** | 6.0 | `تكوين` |
-| التعليمية | **`ال-تعليم-ية`** | 6.0 | `تعليم` |
-| التلفزيونية | **`ال-تلفزيون-ية`** | 6.0 | `تلفزيون` |
-
-### 6.6 Linguistic Interpretation
-
-> **Automated Insight:**
-The language Moroccan Arabic shows high morphological productivity. The subword models are significantly more efficient than word models, suggesting a rich system of affixation or compounding.
-
-> **Note on Idiomaticity:** The high Idiomaticity Gap suggests a large number of frequent multi-word expressions or formulaic sequences that are statistically distinct from their component parts.
+df = pq.read_table("ary_3gram_word.parquet").to_pandas()
+print(df.head())
+```
 
----
-## 7. Summary & Recommendations
+## Models Overview
 
 ![Performance Dashboard](visualizations/performance_dashboard.png)
 
-### Production Recommendations
-
-| Component | Recommended | Rationale |
-|-----------|-------------|-----------|
-| Tokenizer | **64k BPE** | Best compression (4.17x) |
-| N-gram | **2-gram** | Lowest perplexity (424) |
-| Markov | **Context-4** | Highest predictability (97.9%) |
-| Embeddings | **100d** | Balanced semantic capture and isotropy |
-
-
----
-## Appendix: Metrics Glossary & Interpretation Guide
-
-This section provides definitions, intuitions, and guidance for interpreting the metrics used throughout this report.
-
-### Tokenizer Metrics
-
-**Compression Ratio**
-> *Definition:* The ratio of characters to tokens (chars/token). Measures how efficiently the tokenizer represents text.
->
-> *Intuition:* Higher compression means fewer tokens needed to represent the same text, reducing sequence lengths for downstream models. A 3x compression means ~3 characters per token on average.
->
-> *What to seek:* Higher is generally better for efficiency, but extremely high compression may indicate overly aggressive merging that loses morphological information.
-
-**Average Token Length (Fertility)**
-> *Definition:* Mean number of characters per token produced by the tokenizer.
->
-> *Intuition:* Reflects the granularity of tokenization. Longer tokens capture more context but may struggle with rare words; shorter tokens are more flexible but increase sequence length.
->
-> *What to seek:* Balance between 2-5 characters for most languages. Arabic/morphologically-rich languages may benefit from slightly longer tokens.
-
-**Unknown Token Rate (OOV Rate)**
-> *Definition:* Percentage of tokens that map to the unknown/UNK token, indicating words the tokenizer cannot represent.
->
-> *Intuition:* Lower OOV means better vocabulary coverage. High OOV indicates the tokenizer encounters many unseen character sequences.
->
-> *What to seek:* Below 1% is excellent; below 5% is acceptable. BPE tokenizers typically achieve very low OOV due to subword fallback.
-
-### N-gram Model Metrics
-
-**Perplexity**
-> *Definition:* Measures how "surprised" the model is by test data. Mathematically: 2^(cross-entropy). Lower values indicate better prediction.
->
-> *Intuition:* If perplexity is 100, the model is as uncertain as if choosing uniformly among 100 options at each step. A perplexity of 10 means effectively choosing among 10 equally likely options.
->
-> *What to seek:* Lower is better. Perplexity decreases with larger n-grams (more context). Values vary widely by language and corpus size.
-
-**Entropy**
-> *Definition:* Average information content (in bits) needed to encode the next token given the context. Related to perplexity: perplexity = 2^entropy.
->
-> *Intuition:* High entropy means high uncertainty/randomness; low entropy means predictable patterns. Natural language typically has entropy between 1-4 bits per character.
->
-> *What to seek:* Lower entropy indicates more predictable text patterns. Entropy should decrease as n-gram size increases.
-
-**Coverage (Top-K)**
-> *Definition:* Percentage of corpus occurrences explained by the top K most frequent n-grams.
->
-> *Intuition:* High coverage with few patterns indicates repetitive/formulaic text; low coverage suggests diverse vocabulary usage.
->
-> *What to seek:* Depends on use case. For language modeling, moderate coverage (40-60% with top-1000) is typical for natural text.
-
-### Markov Chain Metrics
-
-**Average Entropy**
-> *Definition:* Mean entropy across all contexts, measuring average uncertainty in next-word prediction.
->
-> *Intuition:* Lower entropy means the model is more confident about what comes next. Context-1 has high entropy (many possible next words); Context-4 has low entropy (few likely continuations).
->
-> *What to seek:* Decreasing entropy with larger context sizes. Very low entropy (<0.1) indicates highly deterministic transitions.
-
-**Branching Factor**
-> *Definition:* Average number of unique next tokens observed for each context.
->
-> *Intuition:* High branching = many possible continuations (flexible but uncertain); low branching = few options (predictable but potentially repetitive).
->
-> *What to seek:* Branching factor should decrease with context size. Values near 1.0 indicate nearly deterministic chains.
-
-**Predictability**
-> *Definition:* Derived metric: (1 - normalized_entropy) × 100%. Indicates how deterministic the model's predictions are.
->
-> *Intuition:* 100% predictability means the next word is always certain; 0% means completely random. Real text falls between these extremes.
->
-> *What to seek:* Higher predictability for text generation quality, but too high (>98%) may produce repetitive output.
-
-### Vocabulary & Zipf's Law Metrics
-
-**Zipf's Coefficient**
-> *Definition:* The slope of the log-log plot of word frequency vs. rank. Zipf's law predicts this should be approximately -1.
->
-> *Intuition:* A coefficient near -1 indicates the corpus follows natural language patterns where a few words are very common and most words are rare.
->
-> *What to seek:* Values between -0.8 and -1.2 indicate healthy natural language distribution. Deviations may suggest domain-specific or artificial text.
-
-**R² (Coefficient of Determination)**
-> *Definition:* Measures how well the linear fit explains the frequency-rank relationship. Ranges from 0 to 1.
->
-> *Intuition:* R² near 1.0 means the data closely follows Zipf's law; lower values indicate deviation from expected word frequency patterns.
->
-> *What to seek:* R² > 0.95 is excellent; > 0.99 indicates near-perfect Zipf adherence typical of large natural corpora.
-
-**Vocabulary Coverage**
-> *Definition:* Cumulative percentage of corpus tokens accounted for by the top N words.
->
-> *Intuition:* Shows how concentrated word usage is. If top-100 words cover 50% of text, the corpus relies heavily on common words.
->
-> *What to seek:* Top-100 covering 30-50% is typical. Higher coverage indicates more repetitive text; lower suggests richer vocabulary.
-
-### Word Embedding Metrics
-
-**Isotropy**
-> *Definition:* Measures how uniformly distributed vectors are in the embedding space. Computed as the ratio of minimum to maximum singular values.
->
-> *Intuition:* High isotropy (near 1.0) means vectors spread evenly in all directions; low isotropy means vectors cluster in certain directions, reducing expressiveness.
->
-> *What to seek:* Higher isotropy generally indicates better-quality embeddings. Values > 0.1 are reasonable; > 0.3 is good. Lower-dimensional embeddings tend to have higher isotropy.
-
-**Average Norm**
-> *Definition:* Mean magnitude (L2 norm) of word vectors in the embedding space.
->
-> *Intuition:* Indicates the typical "length" of vectors. Consistent norms suggest stable training; high variance may indicate some words are undertrained.
->
-> *What to seek:* Relatively consistent norms across models. The absolute value matters less than consistency (low std deviation).
-
-**Cosine Similarity**
-> *Definition:* Measures angular similarity between vectors, ranging from -1 (opposite) to 1 (identical direction).
->
-> *Intuition:* Words with similar meanings should have high cosine similarity. This is the standard metric for semantic relatedness in embeddings.
->
-> *What to seek:* Semantically related words should score > 0.5; unrelated words should be near 0. Synonyms often score > 0.7.
-
-**t-SNE Visualization**
-> *Definition:* t-Distributed Stochastic Neighbor Embedding - a dimensionality reduction technique that preserves local structure for visualization.
->
-> *Intuition:* Clusters in t-SNE plots indicate groups of semantically related words. Spread indicates vocabulary diversity; tight clusters suggest semantic coherence.
->
-> *What to seek:* Meaningful clusters (e.g., numbers together, verbs together). Avoid over-interpreting distances - t-SNE preserves local, not global, structure.
-
-### General Interpretation Guidelines
-
-1. **Compare within model families:** Metrics are most meaningful when comparing models of the same type (e.g., 8k vs 64k tokenizer).
-2. **Consider trade-offs:** Better performance on one metric often comes at the cost of another (e.g., compression vs. OOV rate).
-3. **Context matters:** Optimal values depend on downstream tasks. Text generation may prioritize different metrics than classification.
-4. **Corpus influence:** All metrics are influenced by corpus characteristics. Wikipedia text differs from social media or literature.
-5. **Language-specific patterns:** Morphologically rich languages (like Arabic) may show different optimal ranges than analytic languages.
-
-
-### Visualizations Index
-
-| Visualization | Description |
-|---------------|-------------|
-| Tokenizer Compression | Compression ratios by vocabulary size |
-| Tokenizer Fertility | Average token length by vocabulary |
-| Tokenizer OOV | Unknown token rates |
-| Tokenizer Total Tokens | Total tokens by vocabulary |
-| N-gram Perplexity | Perplexity by n-gram size |
-| N-gram Entropy | Entropy by n-gram size |
-| N-gram Coverage | Top pattern coverage |
-| N-gram Unique | Unique n-gram counts |
-| Markov Entropy | Entropy by context size |
-| Markov Branching | Branching factor by context |
-| Markov Contexts | Unique context counts |
-| Zipf's Law | Frequency-rank distribution with fit |
-| Vocab Frequency | Word frequency distribution |
-| Top 20 Words | Most frequent words |
-| Vocab Coverage | Cumulative coverage curve |
-| Embedding Isotropy | Vector space uniformity |
-| Embedding Norms | Vector magnitude distribution |
-| Embedding Similarity | Word similarity heatmap |
-| Nearest Neighbors | Similar words for key terms |
-| t-SNE Words | 2D word embedding visualization |
-| t-SNE Sentences | 2D sentence embedding visualization |
-| Position Encoding | Encoding method comparison |
-| Model Sizes | Storage requirements |
-| Performance Dashboard | Comprehensive performance overview |
+| Category | Assets |
+|----------|--------|
+| Tokenizers | BPE at 8k, 16k, 32k, 64k vocab sizes |
+| N-gram models | 2 / 3 / 4 / 5-gram (word & subword) |
+| Markov chains | Context 1–5 (word & subword) |
+| Embeddings | 32d, 64d, 128d — mono & aligned |
+| Vocabulary | Full frequency list + Zipf analysis |
+| Statistics | Corpus & model statistics JSON |
+
+## Metrics Summary
+
+| Component | Model | Key Metric | Value |
+|-----------|-------|------------|-------|
+| Tokenizer | 8k BPE | Compression | 3.48x |
+| Tokenizer | 16k BPE | Compression | 3.76x |
+| Tokenizer | 32k BPE | Compression | 3.98x |
+| Tokenizer | 64k BPE | Compression | 4.17x 🏆 |
+| N-gram | 2-gram (subword) | Perplexity | 428 🏆 |
+| N-gram | 2-gram (word) | Perplexity | 7,415 |
+| N-gram | 3-gram (subword) | Perplexity | 3,823 |
+| N-gram | 3-gram (word) | Perplexity | 5,775 |
+| N-gram | 4-gram (subword) | Perplexity | 20,320 |
+| N-gram | 4-gram (word) | Perplexity | 8,149 |
+| N-gram | 5-gram (subword) | Perplexity | 63,356 |
+| N-gram | 5-gram (word) | Perplexity | 7,702 |
+| Markov | ctx-1 (subword) | Predictability | 0.0% |
+| Markov | ctx-1 (word) | Predictability | 14.2% |
+| Markov | ctx-2 (subword) | Predictability | 18.4% |
+| Markov | ctx-2 (word) | Predictability | 77.3% |
+| Markov | ctx-3 (subword) | Predictability | 19.7% |
+| Markov | ctx-3 (word) | Predictability | 93.8% |
+| Markov | ctx-4 (subword) | Predictability | 33.7% |
+| Markov | ctx-4 (word) | Predictability | 97.9% 🏆 |
+| Vocabulary | full | Size | 79,667 |
+| Vocabulary | full | Zipf R² | 0.9989 |
+| Embeddings | mono_32d | Isotropy | 0.8215 🏆 |
+| Embeddings | mono_64d | Isotropy | 0.8006 |
+| Embeddings | mono_128d | Isotropy | 0.6555 |
+| Embeddings | aligned_32d | Isotropy | 0.8215 |
+| Embeddings | aligned_64d | Isotropy | 0.8006 |
+| Embeddings | aligned_128d | Isotropy | 0.6555 |
+| Alignment | aligned_32d | R@1 / R@5 / R@10 | 0.8% / 5.8% / 10.8% |
+| Alignment | aligned_64d | R@1 / R@5 / R@10 | 3.8% / 10.0% / 20.0% |
+| Alignment | aligned_128d | R@1 / R@5 / R@10 | 4.4% / 15.6% / 24.2% 🏆 |
+
+📊 **[Full ablation study, per-model breakdowns, and interpretation guide →](RESEARCH_REPORT.md)**
 
 ---
-## About This Project
-
-### Data Source
 
-Models trained on [wikipedia-monthly](https://huggingface.co/datasets/omarkamali/wikipedia-monthly) - a monthly snapshot of Wikipedia articles across 300+ languages.
+## About
 
-### Project
+Trained on [wikipedia-monthly](https://huggingface.co/datasets/omarkamali/wikipedia-monthly) — monthly snapshots of 300+ Wikipedia languages.
 
-A project by **[Wikilangs](https://wikilangs.org)** - Open-source NLP models for every Wikipedia language.
-
-### Maintainer
-
-[Omar Kamali](https://omarkamali.com) - [Omneity Labs](https://omneitylabs.com)
+A project by **[Wikilangs](https://wikilangs.org)** · Maintainer: [Omar Kamali](https://omarkamali.com) · [Omneity Labs](https://omneitylabs.com)
 
 ### Citation
 
-If you use these models in your research, please cite:
-
 ```bibtex
 @misc{wikilangs2025,
-  author = {Kamali, Omar},
-  title = {Wikilangs: Open NLP Models for Wikipedia Languages},
-  year = {2025},
-  doi = {10.5281/zenodo.18073153},
+  author    = {Kamali, Omar},
+  title     = {Wikilangs: Open NLP Models for Wikipedia Languages},
+  year      = {2025},
+  doi       = {10.5281/zenodo.18073153},
   publisher = {Zenodo},
-  url = {https://huggingface.co/wikilangs}
+  url       = {https://huggingface.co/wikilangs},
   institution = {Omneity Labs}
 }
 ```
 
-### License
-
-MIT License - Free for academic and commercial use.
-
 ### Links
 
-- 🌐 Website: [wikilangs.org](https://wikilangs.org)
-- 🤗 Models: [huggingface.co/wikilangs](https://huggingface.co/wikilangs)
-- 📊 Data: [wikipedia-monthly](https://huggingface.co/datasets/omarkamali/wikipedia-monthly)
-- 👤 Author: [Omar Kamali](https://huggingface.co/omarkamali)
+- 🌐 [wikilangs.org](https://wikilangs.org)
+- 🌍 [Language page](https://wikilangs.org/languages/ary/)
+- 🎮 [Playground](https://wikilangs.org/playground/?lang=ary)
+- 🤗 [HuggingFace models](https://huggingface.co/wikilangs)
+- 📊 [wikipedia-monthly dataset](https://huggingface.co/datasets/omarkamali/wikipedia-monthly)
+- 👤 [Omar Kamali](https://huggingface.co/omarkamali)
 - 🤝 Sponsor: [Featherless AI](https://featherless.ai)
----
-*Generated by Wikilangs Models Pipeline*
 
-*Report Date: 2026-01-03 16:42:17*
+**License:** MIT — free for academic and commercial use.
+
+---
+*Generated by Wikilangs Pipeline · 2026-03-02 12:03:27*

RESEARCH_REPORT.md

@@ -0,0 +1,688 @@
+# Moroccan Arabic — Full Ablation Study & Research Report
+
+Detailed evaluation of all model variants trained on **Moroccan Arabic** Wikipedia data by [Wikilangs](https://wikilangs.org).
+
+👈 [Back to README](README.md)
+
+## 📋 Repository Contents
+
+### Models & Assets
+
+- Tokenizers (8k, 16k, 32k, 64k)
+- N-gram models (2, 3, 4, 5-gram)
+- Markov chains (context of 1, 2, 3, 4 and 5)
+- Subword N-gram and Markov chains
+- Embeddings in various sizes and dimensions (aligned and unaligned)
+- Language Vocabulary
+- Language Statistics
+
+![Performance Dashboard](visualizations/performance_dashboard.png)
+
+### Analysis and Evaluation
+
+- [1. Tokenizer Evaluation](#1-tokenizer-evaluation)
+- [2. N-gram Model Evaluation](#2-n-gram-model-evaluation)
+- [3. Markov Chain Evaluation](#3-markov-chain-evaluation)
+- [4. Vocabulary Analysis](#4-vocabulary-analysis)
+- [5. Word Embeddings Evaluation](#5-word-embeddings-evaluation)
+- [6. Morphological Analysis (Experimental)](#6--morphological-analysis-experimental)
+- [7. Summary & Recommendations](#7-summary--recommendations)
+- [Metrics Glossary](#appendix-metrics-glossary--interpretation-guide)
+- [Visualizations Index](#visualizations-index)
+
+---
+## 1. Tokenizer Evaluation
+
+![Tokenizer Compression](visualizations/tokenizer_compression.png)
+
+![Tokenizer Fertility](visualizations/tokenizer_fertility.png)
+
+![Tokenizer OOV](visualizations/tokenizer_oov.png)
+
+![Total Tokens](visualizations/tokenizer_total_tokens.png)
+
+### Results
+
+| Vocab Size | Compression | Avg Token Len | UNK Rate | Total Tokens |
+|------------|-------------|---------------|----------|--------------|
+| **8k** | 3.481x | 3.48 | 0.0910% | 300,053 |
+| **16k** | 3.755x | 3.76 | 0.0982% | 278,145 |
+| **32k** | 3.985x | 3.99 | 0.1041% | 262,127 |
+| **64k** | 4.172x 🏆 | 4.18 | 0.1090% | 250,361 |
+
+### Tokenization Examples
+
+Below are sample sentences tokenized with each vocabulary size:
+
+**Sample 1:** `قريش هيا قبيلة ؤلا أجموع قبلي لي، علا حساب لمصادر لإسلامية، كانت ف مكة ؤ كاينتام...`
+
+| Vocab | Tokens | Count |
+|-------|--------|-------|
+| 8k | `▁ق ريش ▁هيا ▁قبيلة ▁ؤلا ▁أج موع ▁ق بلي ▁لي ... (+19 more)` | 29 |
+| 16k | `▁قريش ▁هيا ▁قبيلة ▁ؤلا ▁أج موع ▁ق بلي ▁لي ، ... (+16 more)` | 26 |
+| 32k | `▁قريش ▁هيا ▁قبيلة ▁ؤلا ▁أجموع ▁ق بلي ▁لي ، ▁علا ... (+15 more)` | 25 |
+| 64k | `▁قريش ▁هيا ▁قبيلة ▁ؤلا ▁أجموع ▁قبلي ▁لي ، ▁علا ▁حساب ... (+14 more)` | 24 |
+
+**Sample 2:** `آيت ميلك جماعة ترابية قروية كاينة في إقليم اشتوكة آيت باها، جهة سوس ماسة، ساكنين...`
+
+| Vocab | Tokens | Count |
+|-------|--------|-------|
+| 8k | `▁آيت ▁ميل ك ▁جماعة ▁ترابية ▁قروية ▁كاينة ▁في ▁إقليم ▁اشتوكة ... (+16 more)` | 26 |
+| 16k | `▁آيت ▁ميل ك ▁جماعة ▁ترابية ▁قروية ▁كاينة ▁في ▁إقليم ▁اشتوكة ... (+16 more)` | 26 |
+| 32k | `▁آيت ▁ميل ك ▁جماعة ▁ترابية ▁قروية ▁كاينة ▁في ▁إقليم ▁اشتوكة ... (+16 more)` | 26 |
+| 64k | `▁آيت ▁ميلك ▁جماعة ▁ترابية ▁قروية ▁كاينة ▁في ▁إقليم ▁اشتوكة ▁آيت ... (+15 more)` | 25 |
+
+**Sample 3:** `خديجة بنت علي بن أبي طالب، هي بنت علي بن أبي طالب. مصادر د نسا`
+
+| Vocab | Tokens | Count |
+|-------|--------|-------|
+| 8k | `▁خديجة ▁بنت ▁علي ▁بن ▁أبي ▁طالب ، ▁هي ▁بنت ▁علي ... (+7 more)` | 17 |
+| 16k | `▁خديجة ▁بنت ▁علي ▁بن ▁أبي ▁طالب ، ▁هي ▁بنت ▁علي ... (+7 more)` | 17 |
+| 32k | `▁خديجة ▁بنت ▁علي ▁بن ▁أبي ▁طالب ، ▁هي ▁بنت ▁علي ... (+7 more)` | 17 |
+| 64k | `▁خديجة ▁بنت ▁علي ▁بن ▁أبي ▁طالب ، ▁هي ▁بنت ▁علي ... (+7 more)` | 17 |
+
+
+### Key Findings
+
+- **Best Compression:** 64k achieves 4.172x compression
+- **Lowest UNK Rate:** 8k with 0.0910% unknown tokens
+- **Trade-off:** Larger vocabularies improve compression but increase model size
+- **Recommendation:** 32k vocabulary provides optimal balance for production use
+
+---
+## 2. N-gram Model Evaluation
+
+![N-gram Perplexity](visualizations/ngram_perplexity.png)
+
+![N-gram Unique](visualizations/ngram_unique.png)
+
+![N-gram Coverage](visualizations/ngram_coverage.png)
+
+### Results
+
+| N-gram | Variant | Perplexity | Entropy | Unique N-grams | Top-100 Coverage | Top-1000 Coverage |
+|--------|---------|------------|---------|----------------|------------------|-------------------|
+| **2-gram** | Word | 7,415 | 12.86 | 40,208 | 22.8% | 50.4% |
+| **2-gram** | Subword | 428 🏆 | 8.74 | 5,913 | 57.8% | 96.3% |
+| **3-gram** | Word | 5,775 | 12.50 | 44,139 | 27.3% | 56.7% |
+| **3-gram** | Subword | 3,823 | 11.90 | 44,840 | 23.0% | 60.5% |
+| **4-gram** | Word | 8,149 | 12.99 | 71,489 | 27.3% | 53.3% |
+| **4-gram** | Subword | 20,320 | 14.31 | 222,645 | 11.9% | 35.8% |
+| **5-gram** | Word | 7,702 | 12.91 | 59,669 | 28.3% | 52.6% |
+| **5-gram** | Subword | 63,356 | 15.95 | 533,903 | 7.3% | 24.8% |
+
+### Top 5 N-grams by Size
+
+**2-grams (Word):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `واصلة ل` | 8,540 |
+| 2 | `نسبة د` | 7,170 |
+| 3 | `ف لمغريب` | 6,310 |
+| 4 | `ف إقليم` | 6,015 |
+| 5 | `ف نسبة` | 4,265 |
+
+**3-grams (Word):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `ف نسبة د` | 4,264 |
+| 2 | `فيها مصدر و` | 3,235 |
+| 3 | `و نسبة د` | 2,894 |
+| 4 | `مصدر و بايت` | 2,855 |
+| 5 | `اللي خدامين ف` | 2,761 |
+
+**4-grams (Word):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `فيها مصدر و بايت` | 2,855 |
+| 2 | `نسبة نّاس اللي خدامين` | 2,705 |
+| 3 | `نّاس اللي خدامين ف` | 2,595 |
+| 4 | `على حساب لإحصاء الرسمي` | 2,501 |
+| 5 | `لمغريب هاد دّوار كينتامي` | 2,500 |
+
+**5-grams (Word):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `نسبة نّاس اللي خدامين ف` | 2,594 |
+| 2 | `ف لمغريب هاد دّوار كينتامي` | 2,500 |
+| 3 | `لمغريب هاد دّوار كينتامي ل` | 2,500 |
+| 4 | `هاد دّوار كينتامي ل مشيخة` | 2,500 |
+| 5 | `حساب لإحصاء الرسمي د عام` | 2,500 |
+
+**2-grams (Subword):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `ا ل` | 348,897 |
+| 2 | `_ ل` | 282,523 |
+| 3 | `ة _` | 230,243 |
+| 4 | `_ ا` | 221,714 |
+| 5 | `_ م` | 157,830 |
+
+**3-grams (Subword):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `_ ا ل` | 216,894 |
+| 2 | `_ ف _` | 84,068 |
+| 3 | `ا ت _` | 64,715 |
+| 4 | `_ و _` | 60,577 |
+| 5 | `ي ة _` | 60,370 |
+
+**4-grams (Subword):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `_ د ي ا` | 48,269 |
+| 2 | `د ي ا ل` | 48,014 |
+| 3 | `ي ا ل _` | 33,434 |
+| 4 | `د _ ا ل` | 33,075 |
+| 5 | `_ م ن _` | 29,173 |
+
+**5-grams (Subword):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `_ د ي ا ل` | 47,884 |
+| 2 | `د ي ا ل _` | 33,006 |
+| 3 | `_ ع ل ى _` | 19,658 |
+| 4 | `_ ا ل ل ي` | 18,939 |
+| 5 | `ا ل ل ي _` | 18,733 |
+
+
+### Key Findings
+
+- **Best Perplexity:** 2-gram (subword) with 428
+- **Entropy Trend:** Decreases with larger n-grams (more predictable)
+- **Coverage:** Top-1000 patterns cover ~25% of corpus
+- **Recommendation:** 4-gram or 5-gram for best predictive performance
+
+---
+## 3. Markov Chain Evaluation
+
+![Markov Entropy](visualizations/markov_entropy.png)
+
+![Markov Contexts](visualizations/markov_contexts.png)
+
+![Markov Branching](visualizations/markov_branching.png)
+
+### Results
+
+| Context | Variant | Avg Entropy | Perplexity | Branching Factor | Unique Contexts | Predictability |
+|---------|---------|-------------|------------|------------------|-----------------|----------------|
+| **1** | Word | 0.8581 | 1.813 | 5.40 | 180,421 | 14.2% |
+| **1** | Subword | 1.1243 | 2.180 | 8.36 | 2,159 | 0.0% |
+| **2** | Word | 0.2267 | 1.170 | 1.49 | 973,633 | 77.3% |
+| **2** | Subword | 0.8165 | 1.761 | 5.10 | 18,051 | 18.4% |
+| **3** | Word | 0.0619 | 1.044 | 1.10 | 1,450,643 | 93.8% |
+| **3** | Subword | 0.8035 | 1.745 | 4.14 | 92,103 | 19.7% |
+| **4** | Word | 0.0207 🏆 | 1.014 | 1.04 | 1,595,675 | 97.9% |
+| **4** | Subword | 0.6627 | 1.583 | 2.87 | 381,563 | 33.7% |
+
+### Generated Text Samples (Word-based)
+
+Below are text samples generated from each word-based Markov chain model:
+
+**Context Size 1:**
+
+1. `ف ايكنان نقص ب سباب غتيال لماليك لأمازيغي ؤ ولّا على المنطق والبحث كان حتا زلزال`
+2. `و نسبة نّاس اللي سبق ليهوم مصادر ربحو جايزة أحسن 10 سنين موراها تولّا لحكم الداتي`
+3. `د لميداليات ف إقليم لحوز جهة مراكش آسفي ف المغرب من بعد باللي كان نتر خيالي`
+
+**Context Size 2:**
+
+1. `واصلة ل 3 ف لعقد ديال عوام كيوافق ف تّقويم لهيجري ؤ ف تّقويم لڭريڭوري بدا نهار`
+2. `نسبة د الشوماج واصلة ل 6 6 044 0 290 يوكطوتانية هيدروجين 7 7 و لخصوبة لكاملة`
+3. `ف لمغريب هاد دّوار كينتامي ل مشيخة أيت قضني لي كتضم 9 د دّواور لعاداد د سّكان`
+
+**Context Size 3:**
+
+1. `ف نسبة د التسكويل واصلة ل 90 8 و نسبة د لأمية واصلة ل 50 33 لخدمة ف`
+2. `فيها مصدر و بايت على حساب النوع د لحنش التشلال التنفوسي فشلان لكبدة لكوما و bites a d`
+3. `و نسبة د الشوماج واصلة ل 18 4 و لموعدّال د لعمر عند الجواج اللولاني هوّ 23 87`
+
+**Context Size 4:**
+
+1. `نسبة نّاس اللي خدامين في لقطاع لخاص 39 1 مصادر الرباط سلا القنيطرة قروية ف إقليم لخميسات مسكونين ف`
+2. `نّاس اللي خدامين ف لپريڤي 57 1 مصادر الرباط سلا القنيطرة قروية ف إقليم سيدي إيفني جهة ݣلميم واد`
+3. `على حساب لإحصاء الرسمي د عام نوطات مصادر ف لمغريب ف إقليم تارودانت زادهوم داريجابوت`
+
+
+### Generated Text Samples (Subword-based)
+
+Below are text samples generated from each subword-based Markov chain model:
+
+**Context Size 1:**
+
+1. `_أو_جة_م_-اسبش_د`
+2. `الاف_ف،_عية_لحدا`
+3. `لعة_ل_وعبر،_اليب`
+
+**Context Size 2:**
+
+1. `الجديات)._عنصاد_ا`
+2. `_لخمسيوسيحطولا_صر`
+3. `ة_ديال_لهي_بزرقة_`
+
+**Context Size 3:**
+
+1. `_اللي_خمائيات_ديال`
+2. `_ف_لجمهورية_الطابل`
+3. `ات_(گاع_ل_من_مابين`
+
+**Context Size 4:**
+
+1. `_ديال_المرسى_ديال_ا`
+2. `ديالهوم_مصادر_فيهم_`
+3. `يال_شيحد_من_بعد_فـ_`
+
+
+### Key Findings
+
+- **Best Predictability:** Context-4 (word) with 97.9% predictability
+- **Branching Factor:** Decreases with context size (more deterministic)
+- **Memory Trade-off:** Larger contexts require more storage (381,563 contexts)
+- **Recommendation:** Context-3 or Context-4 for text generation
+
+---
+## 4. Vocabulary Analysis
+
+![Zipf's Law](visualizations/zipf_law.png)
+
+![Top Words](visualizations/top20_words.png)
+
+![Coverage Curve](visualizations/vocab_coverage.png)
+
+### Statistics
+
+| Metric | Value |
+|--------|-------|
+| Vocabulary Size | 79,667 |
+| Total Tokens | 2,057,009 |
+| Mean Frequency | 25.82 |
+| Median Frequency | 4 |
+| Frequency Std Dev | 518.98 |
+
+### Most Common Words
+
+| Rank | Word | Frequency |
+|------|------|-----------|
+| 1 | ف | 84,381 |
+| 2 | و | 60,856 |
+| 3 | د | 60,420 |
+| 4 | ديال | 32,966 |
+| 5 | من | 29,503 |
+| 6 | ل | 23,808 |
+| 7 | على | 19,757 |
+| 8 | لي | 18,777 |
+| 9 | ب | 17,745 |
+| 10 | اللي | 17,410 |
+
+### Least Common Words (from vocabulary)
+
+| Rank | Word | Frequency |
+|------|------|-----------|
+| 1 | ختيلال | 2 |
+| 2 | تسطية | 2 |
+| 3 | التخمار | 2 |
+| 4 | لمركزين | 2 |
+| 5 | تعلاف | 2 |
+| 6 | الروضيو | 2 |
+| 7 | رِد | 2 |
+| 8 | وينغز | 2 |
+| 9 | تايغرز | 2 |
+| 10 | كلتة | 2 |
+
+### Zipf's Law Analysis
+
+| Metric | Value |
+|--------|-------|
+| Zipf Coefficient | 1.0203 |
+| R² (Goodness of Fit) | 0.998917 |
+| Adherence Quality | **excellent** |
+
+### Coverage Analysis
+
+| Top N Words | Coverage |
+|-------------|----------|
+| Top 100 | 38.4% |
+| Top 1,000 | 62.8% |
+| Top 5,000 | 77.7% |
+| Top 10,000 | 84.1% |
+
+### Key Findings
+
+- **Zipf Compliance:** R²=0.9989 indicates excellent adherence to Zipf's law
+- **High Frequency Dominance:** Top 100 words cover 38.4% of corpus
+- **Long Tail:** 69,667 words needed for remaining 15.9% coverage
+
+---
+## 5. Word Embeddings Evaluation
+
+![Embedding Isotropy](visualizations/embedding_isotropy.png)
+
+![Similarity Matrix](visualizations/embedding_similarity.png)
+
+![t-SNE Words](visualizations/tsne_words.png)
+
+![t-SNE Sentences](visualizations/tsne_sentences.png)
+
+
+### 5.1 Cross-Lingual Alignment
+
+![Alignment Quality](visualizations/embedding_alignment_quality.png)
+
+![Multilingual t-SNE](visualizations/embedding_tsne_multilingual.png)
+
+
+### 5.2 Model Comparison
+
+| Model | Dimension | Isotropy | Semantic Density | Alignment R@1 | Alignment R@10 |
+|-------|-----------|----------|------------------|---------------|----------------|
+| **mono_32d** | 32 | 0.8215 🏆 | 0.3275 | N/A | N/A |
+| **mono_64d** | 64 | 0.8006 | 0.2538 | N/A | N/A |
+| **mono_128d** | 128 | 0.6555 | 0.2039 | N/A | N/A |
+| **aligned_32d** | 32 | 0.8215 | 0.3276 | 0.0080 | 0.1080 |
+| **aligned_64d** | 64 | 0.8006 | 0.2565 | 0.0380 | 0.2000 |
+| **aligned_128d** | 128 | 0.6555 | 0.2044 | 0.0440 | 0.2420 |
+
+### Key Findings
+
+- **Best Isotropy:** mono_32d with 0.8215 (more uniform distribution)
+- **Semantic Density:** Average pairwise similarity of 0.2623. Lower values indicate better semantic separation.
+- **Alignment Quality:** Aligned models achieve up to 4.4% R@1 in cross-lingual retrieval.
+- **Recommendation:** 128d aligned for best cross-lingual performance
+
+---
+## 6.  Morphological Analysis (Experimental)
+
+This section presents an automated morphological analysis derived from the statistical divergence between word-level and subword-level models. By analyzing where subword predictability spikes and where word-level coverage fails, we can infer linguistic structures without supervised data.
+
+### 6.1 Productivity & Complexity
+
+| Metric | Value | Interpretation | Recommendation |
+|--------|-------|----------------|----------------|
+| Productivity Index | **5.000** | High morphological productivity | Reliable analysis |
+| Idiomaticity Gap | **1.121** | High formulaic/idiomatic content | - |
+
+### 6.2 Affix Inventory (Productive Units)
+
+These are the most productive prefixes and suffixes identified by sampling the vocabulary for global substitutability patterns. A unit is considered an affix if stripping it leaves a valid stem that appears in other contexts.
+
+#### Productive Prefixes
+| Prefix | Examples |
+|--------|----------|
+| `-ال` | القوميين, الاحتياطية, الطابلة |
+| `-ل` | لعضان, لكرواتي, لعاميد |
+| `-ت` | تقرا, تحقيقات, تشارلي |
+| `-م` | ميطاكا, معاهد, موليكيلة |
+| `-لم` | لمحلولة, لمقبولين, لمطلوق |
+| `-و` | والهيئات, والطرقان, وبطريقة |
+| `-الم` | المركب, المعروفين, المناخية |
+| `-ب` | بنشليخة, بيئات, بلمارشالية |
+
+#### Productive Suffixes
+| Suffix | Examples |
+|--------|----------|
+| `-ت` | والهيئات, تحقيقات, لبويرات |
+| `-ة` | بنشليخة, وبطريقة, عشبة |
+| `-ات` | والهيئات, تحقيقات, لبويرات |
+| `-ن` | لعضان, والطرقان, القوميين |
+| `-ية` | أكترية, الاحتياطية, والاشتراكية |
+| `-ا` | ميطاكا, تقرا, سيينا |
+| `-ي` | ؤطوماتيكي, لكرواتي, سينتشي |
+| `-ين` | القوميين, پيسّين, مشهورين |
+
+### 6.3 Bound Stems (Lexical Roots)
+
+Bound stems are high-frequency subword units that are semantically cohesive but rarely appear as standalone words. These often correspond to the 'core' of a word that requires inflection or derivation to be valid.
+
+| Stem | Cohesion | Substitutability | Examples |
+|------|----------|------------------|----------|
+| `انية` | 1.84x | 68 contexts | سانية, تانية, غانية |
+| `النا` | 1.79x | 63 contexts | الناي, الناس, النار |
+| `لمغر` | 2.03x | 30 contexts | لمغرب, المغرب, لمغربي |
+| `جماع` | 1.89x | 37 contexts | جماعة, إجماع, جماعي |
+| `اللو` | 1.66x | 61 contexts | اللون, اللور, اللوز |
+| `الات` | 1.59x | 65 contexts | صالات, حالات, سالات |
+| `مغري` | 2.11x | 18 contexts | مغرية, مغريب, لمغريب |
+| `دهوم` | 2.19x | 16 contexts | ضدهوم, يردهوم, جهدهوم |
+| `إحصا` | 2.09x | 17 contexts | إحصاء, لإحصا, إحصائي |
+| `حصاء` | 2.23x | 14 contexts | إحصاء, ليحصاء, لإحصاء |
+| `قليم` | 2.08x | 16 contexts | إقليم, فقليم, اقليم |
+| `لجوا` | 1.76x | 26 contexts | لجواب, الجوا, لجواد |
+
+### 6.4 Affix Compatibility (Co-occurrence)
+
+This table shows which prefixes and suffixes most frequently co-occur on the same stems, revealing the 'stacking' rules of the language's morphology.
+
+| Prefix | Suffix | Frequency | Examples |
+|--------|--------|-----------|----------|
+| `-ال` | `-ة` | 281 words | الرواقية, القهوة |
+| `-ل` | `-ة` | 184 words | لفريسة, للمنصة |
+| `-ال` | `-ت` | 170 words | المجموعات, الصوتيات |
+| `-ال` | `-ات` | 164 words | المجموعات, الصوتيات |
+| `-ال` | `-ية` | 142 words | الرواقية, السيادية |
+| `-ل` | `-ت` | 131 words | لقمقومات, لپوطوات |
+| `-ل` | `-ات` | 125 words | لقمقومات, لپوطوات |
+| `-ل` | `-ن` | 124 words | لعيّان, لخيشوميين |
+| `-ال` | `-ن` | 119 words | الكربون, الفريقين |
+| `-ل` | `-ية` | 116 words | لعدمية, لبيولوجية |
+
+### 6.5 Recursive Morpheme Segmentation
+
+Using **Recursive Hierarchical Substitutability**, we decompose complex words into their constituent morphemes. This approach handles nested affixes (e.g., `prefix-prefix-root-suffix`).
+
+| Word | Suggested Split | Confidence | Stem |
+|------|-----------------|------------|------|
+| والعمالات | **`و-ال-عمالات`** | 7.5 | `عمالات` |
+| والراشيدية | **`و-ال-راشيدية`** | 7.5 | `راشيدية` |
+| والمشروبات | **`و-ال-مشروبات`** | 7.5 | `مشروبات` |
+| والمؤرخين | **`و-ال-مؤرخين`** | 7.5 | `مؤرخين` |
+| والمسيحية | **`و-ال-مسيحية`** | 7.5 | `مسيحية` |
+| فالسعودية | **`ف-ال-سعودية`** | 7.5 | `سعودية` |
+| بالفرنسية | **`ب-ال-فرنسية`** | 7.5 | `فرنسية` |
+| بالكيلوݣرام | **`ب-ال-كيلوݣرام`** | 7.5 | `كيلوݣرام` |
+| والأساتذة | **`و-ال-أساتذة`** | 7.5 | `أساتذة` |
+| والأقاليم | **`و-ال-أقاليم`** | 7.5 | `أقاليم` |
+| باللاتينية | **`ب-ال-لاتينية`** | 7.5 | `لاتينية` |
+| باليونانية | **`ب-ال-يونانية`** | 7.5 | `يونانية` |
+| لبزقوليين | **`لبزقول-ي-ين`** | 7.5 | `ي` |
+| فالجورنال | **`ف-ال-جورنال`** | 7.5 | `جورنال` |
+| بالصيناعة | **`ب-ال-صيناعة`** | 7.5 | `صيناعة` |
+
+### 6.6 Linguistic Interpretation
+
+> **Automated Insight:**
+The language Moroccan Arabic shows high morphological productivity. The subword models are significantly more efficient than word models, suggesting a rich system of affixation or compounding.
+
+> **Note on Idiomaticity:** The high Idiomaticity Gap suggests a large number of frequent multi-word expressions or formulaic sequences that are statistically distinct from their component parts.
+
+---
+## 7. Summary & Recommendations
+
+![Performance Dashboard](visualizations/performance_dashboard.png)
+
+### Production Recommendations
+
+| Component | Recommended | Rationale |
+|-----------|-------------|-----------|
+| Tokenizer | **64k BPE** | Best compression (4.17x) |
+| N-gram | **2-gram** | Lowest perplexity (428) |
+| Markov | **Context-4** | Highest predictability (97.9%) |
+| Embeddings | **100d** | Balanced semantic capture and isotropy |
+
+
+---
+## Appendix: Metrics Glossary & Interpretation Guide
+
+This section provides definitions, intuitions, and guidance for interpreting the metrics used throughout this report.
+
+### Tokenizer Metrics
+
+**Compression Ratio**
+> *Definition:* The ratio of characters to tokens (chars/token). Measures how efficiently the tokenizer represents text.
+>
+> *Intuition:* Higher compression means fewer tokens needed to represent the same text, reducing sequence lengths for downstream models. A 3x compression means ~3 characters per token on average.
+>
+> *What to seek:* Higher is generally better for efficiency, but extremely high compression may indicate overly aggressive merging that loses morphological information.
+
+**Average Token Length (Fertility)**
+> *Definition:* Mean number of characters per token produced by the tokenizer.
+>
+> *Intuition:* Reflects the granularity of tokenization. Longer tokens capture more context but may struggle with rare words; shorter tokens are more flexible but increase sequence length.
+>
+> *What to seek:* Balance between 2-5 characters for most languages. Arabic/morphologically-rich languages may benefit from slightly longer tokens.
+
+**Unknown Token Rate (OOV Rate)**
+> *Definition:* Percentage of tokens that map to the unknown/UNK token, indicating words the tokenizer cannot represent.
+>
+> *Intuition:* Lower OOV means better vocabulary coverage. High OOV indicates the tokenizer encounters many unseen character sequences.
+>
+> *What to seek:* Below 1% is excellent; below 5% is acceptable. BPE tokenizers typically achieve very low OOV due to subword fallback.
+
+### N-gram Model Metrics
+
+**Perplexity**
+> *Definition:* Measures how "surprised" the model is by test data. Mathematically: 2^(cross-entropy). Lower values indicate better prediction.
+>
+> *Intuition:* If perplexity is 100, the model is as uncertain as if choosing uniformly among 100 options at each step. A perplexity of 10 means effectively choosing among 10 equally likely options.
+>
+> *What to seek:* Lower is better. Perplexity decreases with larger n-grams (more context). Values vary widely by language and corpus size.
+
+**Entropy**
+> *Definition:* Average information content (in bits) needed to encode the next token given the context. Related to perplexity: perplexity = 2^entropy.
+>
+> *Intuition:* High entropy means high uncertainty/randomness; low entropy means predictable patterns. Natural language typically has entropy between 1-4 bits per character.
+>
+> *What to seek:* Lower entropy indicates more predictable text patterns. Entropy should decrease as n-gram size increases.
+
+**Coverage (Top-K)**
+> *Definition:* Percentage of corpus occurrences explained by the top K most frequent n-grams.
+>
+> *Intuition:* High coverage with few patterns indicates repetitive/formulaic text; low coverage suggests diverse vocabulary usage.
+>
+> *What to seek:* Depends on use case. For language modeling, moderate coverage (40-60% with top-1000) is typical for natural text.
+
+### Markov Chain Metrics
+
+**Average Entropy**
+> *Definition:* Mean entropy across all contexts, measuring average uncertainty in next-word prediction.
+>
+> *Intuition:* Lower entropy means the model is more confident about what comes next. Context-1 has high entropy (many possible next words); Context-4 has low entropy (few likely continuations).
+>
+> *What to seek:* Decreasing entropy with larger context sizes. Very low entropy (<0.1) indicates highly deterministic transitions.
+
+**Branching Factor**
+> *Definition:* Average number of unique next tokens observed for each context.
+>
+> *Intuition:* High branching = many possible continuations (flexible but uncertain); low branching = few options (predictable but potentially repetitive).
+>
+> *What to seek:* Branching factor should decrease with context size. Values near 1.0 indicate nearly deterministic chains.
+
+**Predictability**
+> *Definition:* Derived metric: (1 - normalized_entropy) × 100%. Indicates how deterministic the model's predictions are.
+>
+> *Intuition:* 100% predictability means the next word is always certain; 0% means completely random. Real text falls between these extremes.
+>
+> *What to seek:* Higher predictability for text generation quality, but too high (>98%) may produce repetitive output.
+
+### Vocabulary & Zipf's Law Metrics
+
+**Zipf's Coefficient**
+> *Definition:* The slope of the log-log plot of word frequency vs. rank. Zipf's law predicts this should be approximately -1.
+>
+> *Intuition:* A coefficient near -1 indicates the corpus follows natural language patterns where a few words are very common and most words are rare.
+>
+> *What to seek:* Values between -0.8 and -1.2 indicate healthy natural language distribution. Deviations may suggest domain-specific or artificial text.
+
+**R² (Coefficient of Determination)**
+> *Definition:* Measures how well the linear fit explains the frequency-rank relationship. Ranges from 0 to 1.
+>
+> *Intuition:* R² near 1.0 means the data closely follows Zipf's law; lower values indicate deviation from expected word frequency patterns.
+>
+> *What to seek:* R² > 0.95 is excellent; > 0.99 indicates near-perfect Zipf adherence typical of large natural corpora.
+
+**Vocabulary Coverage**
+> *Definition:* Cumulative percentage of corpus tokens accounted for by the top N words.
+>
+> *Intuition:* Shows how concentrated word usage is. If top-100 words cover 50% of text, the corpus relies heavily on common words.
+>
+> *What to seek:* Top-100 covering 30-50% is typical. Higher coverage indicates more repetitive text; lower suggests richer vocabulary.
+
+### Word Embedding Metrics
+
+**Isotropy**
+> *Definition:* Measures how uniformly distributed vectors are in the embedding space. Computed as the ratio of minimum to maximum singular values.
+>
+> *Intuition:* High isotropy (near 1.0) means vectors spread evenly in all directions; low isotropy means vectors cluster in certain directions, reducing expressiveness.
+>
+> *What to seek:* Higher isotropy generally indicates better-quality embeddings. Values > 0.1 are reasonable; > 0.3 is good. Lower-dimensional embeddings tend to have higher isotropy.
+
+**Average Norm**
+> *Definition:* Mean magnitude (L2 norm) of word vectors in the embedding space.
+>
+> *Intuition:* Indicates the typical "length" of vectors. Consistent norms suggest stable training; high variance may indicate some words are undertrained.
+>
+> *What to seek:* Relatively consistent norms across models. The absolute value matters less than consistency (low std deviation).
+
+**Cosine Similarity**
+> *Definition:* Measures angular similarity between vectors, ranging from -1 (opposite) to 1 (identical direction).
+>
+> *Intuition:* Words with similar meanings should have high cosine similarity. This is the standard metric for semantic relatedness in embeddings.
+>
+> *What to seek:* Semantically related words should score > 0.5; unrelated words should be near 0. Synonyms often score > 0.7.
+
+**t-SNE Visualization**
+> *Definition:* t-Distributed Stochastic Neighbor Embedding - a dimensionality reduction technique that preserves local structure for visualization.
+>
+> *Intuition:* Clusters in t-SNE plots indicate groups of semantically related words. Spread indicates vocabulary diversity; tight clusters suggest semantic coherence.
+>
+> *What to seek:* Meaningful clusters (e.g., numbers together, verbs together). Avoid over-interpreting distances - t-SNE preserves local, not global, structure.
+
+### General Interpretation Guidelines
+
+1. **Compare within model families:** Metrics are most meaningful when comparing models of the same type (e.g., 8k vs 64k tokenizer).
+2. **Consider trade-offs:** Better performance on one metric often comes at the cost of another (e.g., compression vs. OOV rate).
+3. **Context matters:** Optimal values depend on downstream tasks. Text generation may prioritize different metrics than classification.
+4. **Corpus influence:** All metrics are influenced by corpus characteristics. Wikipedia text differs from social media or literature.
+5. **Language-specific patterns:** Morphologically rich languages (like Arabic) may show different optimal ranges than analytic languages.
+
+
+### Visualizations Index
+
+| Visualization | Description |
+|---------------|-------------|
+| Tokenizer Compression | Compression ratios by vocabulary size |
+| Tokenizer Fertility | Average token length by vocabulary |
+| Tokenizer OOV | Unknown token rates |
+| Tokenizer Total Tokens | Total tokens by vocabulary |
+| N-gram Perplexity | Perplexity by n-gram size |
+| N-gram Entropy | Entropy by n-gram size |
+| N-gram Coverage | Top pattern coverage |
+| N-gram Unique | Unique n-gram counts |
+| Markov Entropy | Entropy by context size |
+| Markov Branching | Branching factor by context |
+| Markov Contexts | Unique context counts |
+| Zipf's Law | Frequency-rank distribution with fit |
+| Vocab Frequency | Word frequency distribution |
+| Top 20 Words | Most frequent words |
+| Vocab Coverage | Cumulative coverage curve |
+| Embedding Isotropy | Vector space uniformity |
+| Embedding Norms | Vector magnitude distribution |
+| Embedding Similarity | Word similarity heatmap |
+| Nearest Neighbors | Similar words for key terms |
+| t-SNE Words | 2D word embedding visualization |
+| t-SNE Sentences | 2D sentence embedding visualization |
+| Position Encoding | Encoding method comparison |
+| Model Sizes | Storage requirements |
+| Performance Dashboard | Comprehensive performance overview |
+
+---
+👈 [Back to README](README.md)
+
+*Generated by Wikilangs Pipeline · 2026-03-02 12:03:50*

models/embeddings/aligned/ary_128d.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec09f2d29ccb3090249f3738f6068e825d70e537decf94ac5428ed8f1bc41e8f
-size 1060912662
+oid sha256:23dd29124172fc87eca0b06da00cc83acbea4338d4ab0bb944c1443f13f8a402
+size 1061407900

models/embeddings/aligned/ary_128d.projection.npy

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d5d793e55a655ac0900c665a7dd2b25bfb2c721388f369f0c888b532aab2b2d
+oid sha256:cf17e00d60be7e77cd190f5673e7b5fb42725875195a574e8af838fe7ab7c4fe
 size 65664

models/embeddings/aligned/ary_128d_metadata.json

@@ -3,6 +3,6 @@
   "dimension": 128,
   "version": "aligned",
   "hub_language": "en",
-  "seed_vocab_size": 3796,
-  "vocab_size": 35328
+  "seed_vocab_size": 3971,
+  "vocab_size": 35802
 }

models/embeddings/aligned/ary_32d.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8540a7a08f8241b60423dc69caaee169822f093e1cf6353b8295063122a7e4bf
-size 265780758
+oid sha256:85ae7c72bcc613fc8ebe04229c068b299fa614cafb556f87a170dec369e8b068
+size 265911964

models/embeddings/aligned/ary_32d.projection.npy

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce8e1e863fb9c4375db9cffb22d2a2c951ffc80e15e09b06bf6aebee82431cd7
+oid sha256:6a4134a5733227be26d45ca94a80c670cff54c5a385ea3abd083727066f0058f
 size 4224

models/embeddings/aligned/ary_32d_metadata.json

@@ -3,6 +3,6 @@
   "dimension": 32,
   "version": "aligned",
   "hub_language": "en",
-  "seed_vocab_size": 3796,
-  "vocab_size": 35328
+  "seed_vocab_size": 3971,
+  "vocab_size": 35802
 }

models/embeddings/aligned/ary_64d.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c1abedc8bbe33e113c64455d6fd411194e4a7ddb5e0a3c659df8c08962758d
-size 530824726
+oid sha256:e0f2ba5eeba6b085b95d8dddb3edbbf6f17c9da5abe2bda71e649e7efa93dba0
+size 531077276

models/embeddings/aligned/ary_64d.projection.npy

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:468aba2325cf26abc86b89cccca9a63ff95115fe381081eceafadf68a2846d6b
+oid sha256:bec30000a60507faa1fe0b953a2e43945709f09dad828de79a04e310e7380831
 size 16512

models/embeddings/aligned/ary_64d_metadata.json

@@ -3,6 +3,6 @@
   "dimension": 64,
   "version": "aligned",
   "hub_language": "en",
-  "seed_vocab_size": 3796,
-  "vocab_size": 35328
+  "seed_vocab_size": 3971,
+  "vocab_size": 35802
 }

models/embeddings/monolingual/ary_128d.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec09f2d29ccb3090249f3738f6068e825d70e537decf94ac5428ed8f1bc41e8f
-size 1060912662
+oid sha256:23dd29124172fc87eca0b06da00cc83acbea4338d4ab0bb944c1443f13f8a402
+size 1061407900

models/embeddings/monolingual/ary_128d_metadata.json

@@ -9,7 +9,8 @@
     "negative": 5,
     "epochs": 5,
     "encoding_method": "rope",
-    "dim": 128
+    "dim": 128,
+    "threads": 40
   },
-  "vocab_size": 35328
+  "vocab_size": 35802
 }

models/embeddings/monolingual/ary_32d.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8540a7a08f8241b60423dc69caaee169822f093e1cf6353b8295063122a7e4bf
-size 265780758
+oid sha256:85ae7c72bcc613fc8ebe04229c068b299fa614cafb556f87a170dec369e8b068
+size 265911964

models/embeddings/monolingual/ary_32d_metadata.json

@@ -9,7 +9,8 @@
     "negative": 5,
     "epochs": 5,
     "encoding_method": "rope",
-    "dim": 32
+    "dim": 32,
+    "threads": 40
   },
-  "vocab_size": 35328
+  "vocab_size": 35802
 }

models/embeddings/monolingual/ary_64d.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c1abedc8bbe33e113c64455d6fd411194e4a7ddb5e0a3c659df8c08962758d
-size 530824726
+oid sha256:e0f2ba5eeba6b085b95d8dddb3edbbf6f17c9da5abe2bda71e649e7efa93dba0
+size 531077276

models/embeddings/monolingual/ary_64d_metadata.json

@@ -9,7 +9,8 @@
     "negative": 5,
     "epochs": 5,
     "encoding_method": "rope",
-    "dim": 64
+    "dim": 64,
+    "threads": 40
   },
-  "vocab_size": 35328
+  "vocab_size": 35802
 }

models/subword_markov/ary_markov_ctx1_subword.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aa85613e52f70b5400e89d68121d9f314136f411cc3b9ddb727f1a18275c75b
-size 139539
+oid sha256:a47d186cfa8ba5504f207f80b2a7ee4d4a993924df44c1e658f81586ab974232
+size 138893

models/subword_markov/ary_markov_ctx1_subword_metadata.json

@@ -2,6 +2,6 @@
   "context_size": 1,
   "variant": "subword",
   "language": "ary",
-  "unique_contexts": 2156,
-  "total_transitions": 11674521
+  "unique_contexts": 2159,
+  "total_transitions": 11813843
 }

models/subword_markov/ary_markov_ctx2_subword.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b46ebfbdafda98e2adad1319ead7fedc44d9204d2776cf2e3205c3bd5f5afebe
-size 797041
+oid sha256:186a66b4aac4749ba72cd645b66d11d219a06361505677603344d72626665cc8
+size 793471

models/subword_markov/ary_markov_ctx2_subword_metadata.json

@@ -2,6 +2,6 @@
   "context_size": 2,
   "variant": "subword",
   "language": "ary",
-  "unique_contexts": 18029,
-  "total_transitions": 11663613
+  "unique_contexts": 18051,
+  "total_transitions": 11802900
 }

models/subword_markov/ary_markov_ctx3_subword.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b4192f99a87bb45ced2563948e266621a565af8ac63ce8f4bde28a93144d756
-size 2874859
+oid sha256:a84fe22f4f1abae384b0dab4be36edac253da06347c8acfe4c377644117593e6
+size 2887510

models/subword_markov/ary_markov_ctx3_subword_metadata.json

@@ -2,6 +2,6 @@
   "context_size": 3,
   "variant": "subword",
   "language": "ary",
-  "unique_contexts": 91858,
-  "total_transitions": 11652705
+  "unique_contexts": 92103,
+  "total_transitions": 11791957
 }

models/subword_markov/ary_markov_ctx4_subword.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aadd6890898708013a847b49d511a4f98c3b4ee57283f361bdeaeedfa6653f41
-size 9246973
+oid sha256:b35928174eefb8cdcf6d948433a4d30d1732c733bee1a59cbf4b1b34a96af4a9
+size 9333153

models/subword_markov/ary_markov_ctx4_subword_metadata.json

@@ -2,6 +2,6 @@
   "context_size": 4,
   "variant": "subword",
   "language": "ary",
-  "unique_contexts": 379445,
-  "total_transitions": 11641797
+  "unique_contexts": 381563,
+  "total_transitions": 11781014
 }

models/subword_ngram/ary_2gram_subword.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85362146166777b9bcdb0f05aa64508022ee248e5e3f69964e1de614c03e7699
-size 83835
+oid sha256:11f67345d6612258f0c36fbcc4ef91d3a4f788f8946cd10aca12fb49e0591722
+size 83143

models/subword_ngram/ary_2gram_subword_metadata.json

@@ -2,6 +2,6 @@
   "n": 2,
   "variant": "subword",
   "language": "ary",
-  "unique_ngrams": 5903,
-  "total_ngrams": 11674521
+  "unique_ngrams": 5913,
+  "total_ngrams": 11813843
 }

models/subword_ngram/ary_3gram_subword.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40969977a99672eecdb27448421f16a3f187d65f3c0dc151cea853e070cbadb7
-size 604436
+oid sha256:731fe728fefb3100db18de2567e0ab19ed6320bc9b3860a656e1b0d723071d5f
+size 605193

models/subword_ngram/ary_3gram_subword_metadata.json

@@ -2,6 +2,6 @@
   "n": 3,
   "variant": "subword",
   "language": "ary",
-  "unique_ngrams": 44651,
-  "total_ngrams": 11663613
+  "unique_ngrams": 44840,
+  "total_ngrams": 11802900
 }

models/subword_ngram/ary_4gram_subword.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2378e1e2d64b3df9e93427a1a78bcd5faaf6ed666409f9219472f778c7c03606
-size 2807017
+oid sha256:2906b0bb46f6eb9129cd9215d946598cc0e16a7cae247295719ba3050cc96116
+size 2842344

models/subword_ngram/ary_4gram_subword_metadata.json

@@ -2,6 +2,6 @@
   "n": 4,
   "variant": "subword",
   "language": "ary",
-  "unique_ngrams": 220807,
-  "total_ngrams": 11652705
+  "unique_ngrams": 222645,
+  "total_ngrams": 11791957
 }

models/subword_ngram/ary_5gram_subword.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf8ee4ec12ef42cd5e3558d66ad4aeff0631f166fba66070e4e84f08a774416
-size 7211281
+oid sha256:533843b27ab76aad1a2125aba30039074abf08adaee6e22d0fe500236c06a257
+size 7278591

models/subword_ngram/ary_5gram_subword_metadata.json

@@ -2,6 +2,6 @@
   "n": 5,
   "variant": "subword",
   "language": "ary",
-  "unique_ngrams": 527725,
-  "total_ngrams": 11641797
+  "unique_ngrams": 533903,
+  "total_ngrams": 11781014
 }

models/tokenizer/ary_tokenizer_16k.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1180ec148decdb3ef68cab243d4b164e40e6f3a9cd004c5a4a6675974d1751d6
-size 559287
+oid sha256:f4d5e32d06745b883de576bf9b8e04f6b546761414ef32c72ce2e58c2493d6f2
+size 558827

models/tokenizer/ary_tokenizer_32k.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62ead2fffa727c9fa33838adbab2d6cfe8e11b224486009a2df8900f2a79d842
-size 891778
+oid sha256:a7d26a99b4d6eaba0bf6312cb2107eb329d0d96c3e427e621e8b0750a99f2374
+size 891273

models/tokenizer/ary_tokenizer_64k.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cc3477018e21f222e7e79316e39de3e66d54eaa975a1b19e66cb19ef807cd23
-size 1592960
+oid sha256:3d3dc68570a8afe23be4f8d6f0d33b09f73fc4cd0a38ab57824a5bc552a1eeb9
+size 1592537

models/tokenizer/ary_tokenizer_8k.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c9d36c71b1333556ef6580bcbbd43671c35b88296320664be74ffda2b47642c
-size 396519
+oid sha256:8ef26d909eaf49e80af1cd939826a6e5d8ecab53a921532d6dd5019f91013175
+size 396383

models/vocabulary/ary_vocabulary.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06972d02fe5edd7023b3c7da816f69a17e6b3e79183317908fa5f435bcd3fe0b
-size 1396990
+oid sha256:ae2ef916c872a66f5ac3b2a576a30a32773cb05153f900a81655c67a9a53d98d
+size 1426642

models/vocabulary/ary_vocabulary_metadata.json

@@ -1,17 +1,17 @@
 {
   "language": "ary",
-  "vocabulary_size": 78779,
+  "vocabulary_size": 79667,
   "variant": "full",
   "statistics": {
-    "type_token_ratio": 0.0838713972533892,
+    "type_token_ratio": 0.08362757688063684,
     "coverage": {
-      "top_100": 0.36742576968301266,
-      "top_1000": 0.5995843327288514,
-      "top_5000": 0.7413866015051412,
-      "top_10000": 0.8022598684642346
+      "top_100": 0.366426714703403,
+      "top_1000": 0.5985740986276256,
+      "top_5000": 0.7404440555697419,
+      "top_10000": 0.8014438827079335
     },
-    "hapax_count": 100115,
-    "hapax_ratio": 0.5596330788064441,
-    "total_documents": 10908
+    "hapax_count": 100784,
+    "hapax_ratio": 0.558511728945808,
+    "total_documents": 10943
   }
 }

models/word_markov/ary_markov_ctx1_word.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a010a2fee1638b81b95efa703c67ec669457295da9be4b0fd98080b9fa5269b
-size 10613710
+oid sha256:ea031ad3bae66c0cd73c32d8253f69299f69d10016ee3f7ed372ca7d93a180dd
+size 10728094

models/word_markov/ary_markov_ctx1_word_metadata.json

@@ -2,6 +2,6 @@
   "context_size": 1,
   "variant": "word",
   "language": "ary",
-  "unique_contexts": 178865,
-  "total_transitions": 2122048
+  "unique_contexts": 180421,
+  "total_transitions": 2146850
 }

models/word_markov/ary_markov_ctx2_word.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:712f90109dc88d6441f66e51cbe823ae8692297f944de4a533056a1db4fd292f
-size 26628986
+oid sha256:b484e89a2f5ad24d4011e063ffd1dfcceaa56a738004916a9aff590bcdc9eb02
+size 26992628

models/word_markov/ary_markov_ctx2_word_metadata.json

@@ -2,6 +2,6 @@
   "context_size": 2,
   "variant": "word",
   "language": "ary",
-  "unique_contexts": 962233,
-  "total_transitions": 2111140
+  "unique_contexts": 973633,
+  "total_transitions": 2135907
 }

models/word_markov/ary_markov_ctx3_word.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f27df8a6b3c1b3e0c9195f59edb4203d0589a76026e8e82991c554cda82d38f
-size 36690145
+oid sha256:7131ba67344fb5d89210dc4d2112f8cc84f31f8e36fb9130be3ca9cf72dc830f
+size 37168553

models/word_markov/ary_markov_ctx3_word_metadata.json

@@ -2,6 +2,6 @@
   "context_size": 3,
   "variant": "word",
   "language": "ary",
-  "unique_contexts": 1431084,
-  "total_transitions": 2100232
+  "unique_contexts": 1450643,
+  "total_transitions": 2124964
 }