Upload all models and assets for zgh (latest)

.gitattributes

@@ -33,3 +33,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+visualizations/embedding_similarity.png filter=lfs diff=lfs merge=lfs -text
+visualizations/embedding_tsne_multilingual.png filter=lfs diff=lfs merge=lfs -text
+visualizations/performance_dashboard.png filter=lfs diff=lfs merge=lfs -text
+visualizations/position_encoding_comparison.png filter=lfs diff=lfs merge=lfs -text
+visualizations/tsne_sentences.png filter=lfs diff=lfs merge=lfs -text
+visualizations/tsne_words.png filter=lfs diff=lfs merge=lfs -text
+visualizations/zipf_law.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,773 @@
+---
+language: zgh
+language_name: Standard Moroccan Tamazight
+language_family: berber
+tags:
+  - wikilangs
+  - nlp
+  - tokenizer
+  - embeddings
+  - n-gram
+  - markov
+  - wikipedia
+  - feature-extraction
+  - sentence-similarity
+  - tokenization
+  - n-grams
+  - markov-chain
+  - text-mining
+  - fasttext
+  - babelvec
+  - vocabulous
+  - vocabulary
+  - monolingual
+  - family-berber
+license: mit
+library_name: wikilangs
+pipeline_tag: text-generation
+datasets:
+  - omarkamali/wikipedia-monthly
+dataset_info:
+  name: wikipedia-monthly
+  description: Monthly snapshots of Wikipedia articles across 300+ languages
+metrics:
+  - name: best_compression_ratio
+    type: compression
+    value: 3.844
+  - name: best_isotropy
+    type: isotropy
+    value: 0.7259
+  - name: vocabulary_size
+    type: vocab
+    value: 0
+generated: 2026-01-11
+---
+
+# Standard Moroccan Tamazight - Wikilangs Models
+## Comprehensive Research Report & Full Ablation Study
+
+This repository contains NLP models trained and evaluated by Wikilangs, specifically on **Standard Moroccan Tamazight** Wikipedia data.
+We analyze tokenizers, n-gram models, Markov chains, vocabulary statistics, and word embeddings.
+
+## 📋 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** | 3.062x | 3.07 | 0.9549% | 377,124 |
+| **16k** | 3.360x | 3.36 | 1.0478% | 343,658 |
+| **32k** | 3.609x | 3.61 | 1.1257% | 319,893 |
+| **64k** | 3.844x 🏆 | 3.85 | 1.1990% | 300,327 |
+
+### Tokenization Examples
+
+Below are sample sentences tokenized with each vocabulary size:
+
+**Sample 1:** `thumb ⴱⵉ ⴱⵉ ⵙⵉ ⵏⵖ BBC (ⵙ ⵜⵏⴳⵍⵉⵣⵜ: British Broadcasting Corporation) ⵉⵙⴰⵖⵓⵍⵏ`
+
+| Vocab | Tokens | Count |
+|-------|--------|-------|
+| 8k | `▁thumb ▁ⴱⵉ ▁ⴱⵉ ▁ⵙⵉ ▁ⵏⵖ ▁b bc ▁( ⵙ ▁ⵜⵏⴳⵍⵉⵣⵜ ... (+16 more)` | 26 |
+| 16k | `▁thumb ▁ⴱⵉ ▁ⴱⵉ ▁ⵙⵉ ▁ⵏⵖ ▁bbc ▁( ⵙ ▁ⵜⵏⴳⵍⵉⵣⵜ : ... (+9 more)` | 19 |
+| 32k | `▁thumb ▁ⴱⵉ ▁ⴱⵉ ▁ⵙⵉ ▁ⵏⵖ ▁bbc ▁( ⵙ ▁ⵜⵏⴳⵍⵉⵣⵜ : ... (+8 more)` | 18 |
+| 64k | `▁thumb ▁ⴱⵉ ▁ⴱⵉ ▁ⵙⵉ ▁ⵏⵖ ▁bbc ▁( ⵙ ▁ⵜⵏⴳⵍⵉⵣⵜ : ... (+5 more)` | 15 |
+
+**Sample 2:** `ⴰⴳⴰⴷⴰⵣ ⴰⴼⵕⴰⵏⵚⵉⵚ ⵉⴳⴰ ⴰⴳⴷⵓⵣ ⴷ ⴰⵙⴷⴷⵉ ⵏ ⵡⴰⵙⵖⵏⵣⵉ ⴳ ⵜⴰⴷⴷⵓⵔⵜ ⵜⴰⴼⵕⴰⵏⵚⵉⵚⵜ, ⵏ ⵓⵔⵍⵢⴰⵏⵣ ⴰⵎⴰⵢ...`
+
+| Vocab | Tokens | Count |
+|-------|--------|-------|
+| 8k | `▁ⴰⴳⴰ ⴷⴰⵣ ▁ⴰⴼⵕⴰⵏⵚⵉⵚ ▁ⵉⴳⴰ ▁ⴰⴳⴷ ⵓⵣ ▁ⴷ ▁ⴰⵙⴷⴷⵉ ▁ⵏ ▁ⵡⴰⵙ ... (+19 more)` | 29 |
+| 16k | `▁ⴰⴳⴰⴷⴰⵣ ▁ⴰⴼⵕⴰⵏⵚⵉⵚ ▁ⵉⴳⴰ ▁ⴰⴳⴷ ⵓⵣ ▁ⴷ ▁ⴰⵙⴷⴷⵉ ▁ⵏ ▁ⵡⴰⵙ ⵖⵏⵣⵉ ... (+17 more)` | 27 |
+| 32k | `▁ⴰⴳⴰⴷⴰⵣ ▁ⴰⴼⵕⴰⵏⵚⵉⵚ ▁ⵉⴳⴰ ▁ⴰⴳⴷ ⵓⵣ ▁ⴷ ▁ⴰⵙⴷⴷⵉ ▁ⵏ ▁ⵡⴰⵙ ⵖⵏⵣⵉ ... (+17 more)` | 27 |
+| 64k | `▁ⴰⴳⴰⴷⴰⵣ ▁ⴰⴼⵕⴰⵏⵚⵉⵚ ▁ⵉⴳⴰ ▁ⴰⴳⴷ ⵓⵣ ▁ⴷ ▁ⴰⵙⴷⴷⵉ ▁ⵏ ▁ⵡⴰⵙ ⵖⵏⵣⵉ ... (+11 more)` | 21 |
+
+**Sample 3:** `ⵄⴱⴷⵍⴼⵜⵜⴰⵃ ⵙⵙⵉⵙⵉ (ⵙ ⵜⴰⵄⵕⴰⴱⵜ: عبد الفتاح السيسي), ⵉⵍⵓⵍ ⴳ 19 ⵏⵓⵡⴰⵏⴱⵉⵔ ⴳ ⵜⵇⴰⵀⵉⵔⵜ, ⵉⴳ...`
+
+| Vocab | Tokens | Count |
+|-------|--------|-------|
+| 8k | `▁ⵄⴱⴷ ⵍⴼ ⵜⵜⴰ ⵃ ▁ⵙⵙⵉ ⵙⵉ ▁( ⵙ ▁ⵜⴰⵄⵕⴰⴱⵜ : ... (+40 more)` | 50 |
+| 16k | `▁ⵄⴱⴷ ⵍⴼ ⵜⵜⴰ ⵃ ▁ⵙⵙⵉ ⵙⵉ ▁( ⵙ ▁ⵜⴰⵄⵕ��ⴱⵜ : ... (+38 more)` | 48 |
+| 32k | `▁ⵄⴱⴷⵍⴼ ⵜⵜⴰⵃ ▁ⵙⵙⵉⵙⵉ ▁( ⵙ ▁ⵜⴰⵄⵕⴰⴱⵜ : ▁عبد ▁الف ت ... (+34 more)` | 44 |
+| 64k | `▁ⵄⴱⴷⵍⴼ ⵜⵜⴰⵃ ▁ⵙⵙⵉⵙⵉ ▁( ⵙ ▁ⵜⴰⵄⵕⴰⴱⵜ : ▁عبد ▁الفتاح ▁السيسي ... (+27 more)` | 37 |
+
+
+### Key Findings
+
+- **Best Compression:** 64k achieves 3.844x compression
+- **Lowest UNK Rate:** 8k with 0.9549% 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 | 1,196 | 10.22 | 27,047 | 45.0% | 79.1% |
+| **2-gram** | Subword | 278 🏆 | 8.12 | 3,951 | 66.4% | 98.7% |
+| **3-gram** | Word | 1,791 | 10.81 | 50,741 | 39.8% | 75.1% |
+| **3-gram** | Subword | 1,389 | 10.44 | 30,764 | 34.7% | 83.1% |
+| **4-gram** | Word | 3,181 | 11.64 | 96,325 | 36.3% | 68.2% |
+| **4-gram** | Subword | 3,814 | 11.90 | 123,122 | 22.6% | 70.8% |
+| **5-gram** | Word | 3,890 | 11.93 | 104,452 | 36.6% | 65.2% |
+| **5-gram** | Subword | 6,884 | 12.75 | 251,758 | 17.4% | 65.2% |
+
+### Top 5 N-grams by Size
+
+**2-grams (Word):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `ⵜⴳⵎⵉⴹⵉ ⵏ` | 30,065 |
+| 2 | `ⵏ ⵓⵙⴳⴳⵯⴰⵙ` | 27,531 |
+| 3 | `ⵓⵎⴹⴰⵏ ⵏ` | 26,944 |
+| 4 | `ⵏ ⵉⵎⵣⴷⴰⵖⵏ` | 24,199 |
+| 5 | `ⵜⵍⴽⵎ ⵜⴳⵎⵉⴹⵉ` | 24,115 |
+
+**3-grams (Word):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `ⵜⵍⴽⵎ ⵜⴳⵎⵉⴹⵉ ⵏ` | 24,115 |
+| 2 | `ⵓⵎⴹⴰⵏ ⵏ ⵉⵎⵣⴷⴰⵖⵏ` | 14,960 |
+| 3 | `ⵜⴰⵎⴰⵜⵜⴰⵢⵜ ⵏ ⵓⵙⵖⵉⵡⵙ` | 14,959 |
+| 4 | `ⵜⴰⵙⵎⵉⵔⵉⵜ ⵜⴰⵎⴰⵜⵜⴰⵢⵜ ⵏ` | 14,958 |
+| 5 | `ⴳ ⵜⵍⴽⵎ ⵜⴳⵎⵉⴹⵉ` | 12,063 |
+
+**4-grams (Word):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `ⵜⴰⵙⵎⵉⵔⵉⵜ ⵜⴰⵎⴰⵜⵜⴰⵢⵜ ⵏ ⵓⵙⵖⵉⵡⵙ` | 14,958 |
+| 2 | `ⴳ ⵜⵍⴽⵎ ⵜⴳⵎⵉⴹⵉ ⵏ` | 12,063 |
+| 3 | `ⵓⵎⴹⴰⵏ ⵏ ⵉⵎⵣⴷⴰⵖⵏ ⵏⵏⵙ` | 8,928 |
+| 4 | `ⵉⵎⵣⴷⴰⵖⵏ ⵜⴰⵙⵎⵉⵔⵉⵜ ⵜⴰⵎⴰⵜⵜⴰⵢⵜ ⵏ` | 8,927 |
+| 5 | `ⴰⵎⴰⵜⴰⵢ ⵏ ⵉⵎⵣⴷⴰⵖⵏ ⵜⴰⵙⵎⵉⵔⵉⵜ` | 8,927 |
+
+**5-grams (Word):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `ⵏ ⵉⵎⵣⴷⴰⵖⵏ ⵜⴰⵙⵎⵉⵔⵉⵜ ⵜⴰⵎⴰⵜⵜⴰⵢⵜ ⵏ` | 8,927 |
+| 2 | `ⴰⵎⴰⵜⴰⵢ ⵏ ⵉⵎⵣⴷⴰⵖⵏ ⵜⴰⵙⵎⵉⵔⵉⵜ ⵜⴰⵎⴰⵜⵜⴰⵢⵜ` | 8,927 |
+| 3 | `ⵉⵎⵣⴷⴰⵖⵏ ⵜⴰⵙⵎⵉⵔⵉⵜ ⵜⴰⵎⴰⵜⵜⴰⵢⵜ ⵏ ⵓⵙⵖⵉⵡⵙ` | 8,927 |
+| 4 | `ⵉⴹⴼⴰⵕ ⵓⵙⵓⵏ ⴰⴷ ⵉ ⵜⵔⴼⵉⵇⵜ` | 8,926 |
+| 5 | `ⵍⵎⵖⵔⵉⴱ ⵉⴹⴼⴰⵕ ⵓⵙⵓⵏ ⴰⴷ ⵉ` | 8,926 |
+
+**2-grams (Subword):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `ⵏ _` | 653,035 |
+| 2 | `_ ⵏ` | 397,792 |
+| 3 | `_ ⵜ` | 364,082 |
+| 4 | `_ ⵉ` | 257,899 |
+| 5 | `_ ⵓ` | 211,446 |
+
+**3-grams (Subword):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `_ ⵏ _` | 291,650 |
+| 2 | `_ ⵜ ⴰ` | 138,650 |
+| 3 | `_ ⴳ _` | 115,983 |
+| 4 | `ⵏ _ ⵉ` | 106,477 |
+| 5 | `ⴰ ⵏ _` | 105,784 |
+
+**4-grams (Subword):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `_ ⵏ _ ⵓ` | 86,083 |
+| 2 | `ⵜ _ ⵏ _` | 65,334 |
+| 3 | `_ ⵏ _ ⵉ` | 62,419 |
+| 4 | `ⵏ _ ⵓ ⵙ` | 60,609 |
+| 5 | `_ ⵏ _ ⵜ` | 57,983 |
+
+**5-grams (Subword):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `_ ⵏ _ ⵓ ⵙ` | 51,067 |
+| 2 | `ⵎ ⵣ ⴷ ⴰ ⵖ` | 45,993 |
+| 3 | `ⴳ ⴳ ⵯ ⴰ ⵙ` | 36,185 |
+| 4 | `ⵙ ⴳ ⴳ ⵯ ⴰ` | 36,178 |
+| 5 | `_ ⵏ ⵏ ⴰ _` | 35,864 |
+
+
+### Key Findings
+
+- **Best Perplexity:** 2-gram (subword) with 278
+- **Entropy Trend:** Decreases with larger n-grams (more predictable)
+- **Coverage:** Top-1000 patterns cover ~65% 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 | 0.6673 | 1.588 | 4.36 | 83,258 | 33.3% |
+| **1** | Subword | 1.0864 | 2.123 | 8.88 | 1,091 | 0.0% |
+| **2** | Word | 0.2718 | 1.207 | 1.69 | 361,700 | 72.8% |
+| **2** | Subword | 0.9804 | 1.973 | 6.14 | 9,682 | 2.0% |
+| **3** | Word | 0.0879 | 1.063 | 1.19 | 608,815 | 91.2% |
+| **3** | Subword | 0.8161 | 1.761 | 3.76 | 59,433 | 18.4% |
+| **4** | Word | 0.0448 🏆 | 1.032 | 1.12 | 719,950 | 95.5% |
+| **4** | Subword | 0.5524 | 1.466 | 2.41 | 223,378 | 44.8% |
+
+### Generated Text Samples (Word-based)
+
+Below are text samples generated from each word-based Markov chain model:
+
+**Context Size 1:**
+
+1. `ⵏ ⵜⴰⵚⵚⵓⵕⵜ ⵜⴰⵎⵏⴰⴹⵜ ⵏ 800 ⵏ ⵜⴰⵎⴹⵉⵜ ⵙ ⵜⴳⵎⵉⴹⵉ ⵏ ⵍⵎⵏⵣⵍ ⵜⴰⵙⴳⴰ ⵏ ⵓⵙⵍⵎⴷ 95 ⵏ`
+2. `ⴳ ⵜⵍⴽⵎ ⵜⴳⵎⵉⴹⵉ ⵏ ⵜⵎⵍⵙⴰ ⵢⴰⴹⵏⵉ ⵣⵓⵏ ⴷ 11 ⵏ ⵢⵉⵡⵍ ⴰⵎⵣⵡⴰⵔⵓ 33 85 37 5`
+3. `ⴷ ⵉⵔⴰⵔ ⵍⵎⵖⵔⵉⴱ ⵉⴹⴼⴰⵕ ⵓⵙⵓⵏ ⵉⵎⵓⵏⵏ ⵢⵉⵍⵉ ⴳ ⵓⵙⵉⴹⵏ ⴰⵎⴰⴷⴷⵓⴷ ⵏ ⵜⴳⵍⴷⵉⵜ ⵜⴰⵙⴰⵄⵓⴷⵉⵜ ⴳ ⵜⴳⵔⴰⵡⵜ ⵏ`
+
+**Context Size 2:**
+
+1. `ⵜⴳⵎⵉⴹⵉ ⵏ ⵎⴷⴷ ⵏⵏⴰ ⵥⴹⴰⵕⵏⵉⵏ ⵉ ⵜⵡⵓⵔⵉ 53 52 ⴳ ⴰⵢⵜ ⵄⵍⵍⴰ ⵏⵏⴰ ⴳ ⵍⵍⴰⵏ 5 ⵏ`
+2. `ⵏ ⵓⵙⴳⴳⵯⴰⵙ démographiques et socio économiques de la population et de l habitat de ⵜⴰⵙⵎⵉⵔⵉⵜ ⵜⴰⵎⴰⵜⵜⴰⵢⵜ...`
+3. `ⵓⵎⴹⴰⵏ ⵏ ⵉⵎⵣⴷⴰⵖⵏ ⵏⵏⵙ 75 ⵏ ⵜⵡⵜⵎⵉⵏ ⵜⴰⵡⵊⵉⵡⵉⵏ ⵉⵡⵍ ⴷ ⵜⴰⵔⵡⴰ ⴳ ⴳⴰⵏ ⵡⵉⵏⴰ ⵢⵉⵡⵍⵏ ⴳ ⵓⵙⵓⵏ`
+
+**Context Size 3:**
+
+1. `ⵜⵍⴽⵎ ⵜⴳⵎⵉⴹⵉ ⵏ ⵜⴰⵔⵙⴽⴽⵉⵍⵜ 50 98 ⴳⵔ ⵉⵔⴱⴰⵏ ⴷ ⵜⵔⴱⴰⵜⵉⵏ ⵏⵏⴰ ⵖⵓⵔ ⴳⵔ 6 ⴷ 11 ⵏ ⵓⵙⴳⴳⵯⴰⵙ`
+2. `ⵓⵎⴹⴰⵏ ⵏ ⵉⵎⵣⴷⴰⵖⵏ ⵏⵏⵙ 122 ⵏ ⵓⵎⵣⴷⴰⵖ ⴳ ⵓⵙⵉⴹⵏ ⴰⵎⴰⴷⴷⵓⴷ ⵏ ⵓⵙⴳⴳⵯⴰⵙ démographiques et socio économiques de la`
+3. `ⵜⴰⵎⴰⵜⵜⴰⵢⵜ ⵏ ⵓⵙⵖⵉⵡⵙ ⴰⵕⵛⵉⴼ 14 ⵖⵓⵛⵜ ⵜⵉⵙⵏⴰⴷⴷⴰⴷⵉⵏ ⵜⵉⵙⵏⴰⴷⴷⴰⴷⵉⵏ ⵜⵉⵎⴰⵜⴰⵢⵉⵏ ⵉⴳⴳⵯⵉⵣ ⵓⵎⴹⴰⵏ ⵏ ⵉⵎⵣⴷⴰⵖⵏ ⵏ ⵜⴰⵖⵣⵓⵜ ⵙ...`
+
+**Context Size 4:**
+
+1. `ⵜⴰⵙⵎⵉⵔⵉⵜ ⵜⴰⵎⴰⵜⵜⴰⵢⵜ ⵏ ⵓⵙⵖⵉⵡⵙ ⴰⵕⵛⵉⴼ 14 ⵖⵓⵛⵜ ⵜⵉⵙⵏⴰⴷⴷⴰⴷⵉⵏ ⵜⵉⵙⵏⴰⴷⴷⴰⴷⵉⵏ ⵜⵉⵎⴰⵜⴰⵢⵉⵏ ⵉⴳⴳⵯⵉⵣ ⵓⵎⴹⴰⵏ ⵏ ⵉⵎⵣⴷⴰⵖⵏ ⵏ...`
+2. `ⴳ ⵜⵍⴽⵎ ⵜⴳⵎⵉⴹⵉ ⵏ ⵎⴷⴷ ⵏⵏⴰ ⵥⴹⴰⵕⵏⵉⵏ ⵉ ⵜⵡⵓⵔⵉ 55 29 ⴳ ⴰⵢⵜ ⴱⵏ ⵄⴱⴱⵓ ⴰⵔ ⵏⵉⵜ ⵙⵡⵓⵔⵉⵏ ⵏⵉⵖ`
+3. `ⵓⵎⴹⴰⵏ ⵏ ⵉⵎⵣⴷⴰⵖⵏ ⵏⵏⵙ 390 ⵏ ⵓⵎⵣⴷⴰⵖ ⴳ ⵓⵙⵉⴹⵏ ⴰⵎⴰⴷⴷⵓⴷ ⵏ ⵓⵙⴳⴳⵯⴰⵙ démographiques et socio économiques de la...`
+
+
+### Generated Text Samples (Subword-based)
+
+Below are text samples generated from each subword-based Markov chain model:
+
+**Context Size 1:**
+
+1. `_ⵜⴰⵢⵢⵉⵏⴰⵔ_ⴱⵜⴰⵏ_ⵓ`
+2. `ⴰⵖⵉⵜ_ⵖⵜ_ⵇⵏ_ⴳ_non`
+3. `ⵏ_ⵉⵇⵜⴰ_ⵏ_ⵓⵎⴹⵏ_ⴼⵜ`
+
+**Context Size 2:**
+
+1. `ⵏ_ⴷ_ⵉⴳⴳⵉⵙⵙ_3_ⴰⵍ_ⴰ`
+2. `_ⵏ_ⴰⵎⴰⵏ_ⴳ_ⵓⵙⵙⴰⵖⵏ_`
+3. `_ⵜⵡⵓⵔ_6_ⴽⵓⴷⴰⵖ,_ⵉⵥ`
+
+**Context Size 3:**
+
+1. `_ⵏ_ⵜⴰⵙⵡⵉⵏ_ⵉⵙⴽⴰⵔⵏⵜ_`
+2. `_ⵜⴰⵡⵓⵔⵉ_4.52%_ⴳⵔ_6`
+3. `_ⴳ_ⵍⵍⴰⵏ_ⵡⵉⵏ:_ⵉⵡⵜⵎⵉ`
+
+**Context Size 4:**
+
+1. `_ⵏ_ⵓⵍⴰ_ⴳ_ⴳⴰⵏ_ⵡⵉⵏⴰ_ⵢ`
+2. `ⵜ_ⵏ_ⵓⵙⵖⵉⵡⵙ._ⴰⵕⵛⵉⴼ,_`
+3. `_ⵏ_ⵉⵡⵜⵎⴰⵏ_ⴷ_24.85,_`
+
+
+### Key Findings
+
+- **Best Predictability:** Context-4 (word) with 95.5% predictability
+- **Branching Factor:** Decreases with context size (more deterministic)
+- **Memory Trade-off:** Larger contexts require more storage (223,378 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 | 35,191 |
+| Total Tokens | 2,431,531 |
+| Mean Frequency | 69.10 |
+| Median Frequency | 4 |
+| Frequency Std Dev | 1880.39 |
+
+### Most Common Words
+
+| Rank | Word | Frequency |
+|------|------|-----------|
+| 1 | ⵏ | 291,759 |
+| 2 | ⴳ | 116,564 |
+| 3 | ⴷ | 74,542 |
+| 4 | ⵙ | 39,445 |
+| 5 | ⵏⵏⴰ | 35,886 |
+| 6 | ⴳⵔ | 30,891 |
+| 7 | ⵉⵎⵣⴷⴰⵖⵏ | 30,462 |
+| 8 | ⵜⴳⵎⵉⴹⵉ | 30,068 |
+| 9 | ⵓⵙⴳⴳⵯⴰⵙ | 29,018 |
+| 10 | ⵓⵎⴹⴰⵏ | 27,041 |
+
+### Least Common Words (from vocabulary)
+
+| Rank | Word | Frequency |
+|------|------|-----------|
+| 1 | ⵓⵎⵙⵙⵉⵥⵉⵕ | 2 |
+| 2 | ⵜⵙⵔⴽⵎⵉⵏ | 2 |
+| 3 | ⵓⵎⵢⴰⴱⴰ | 2 |
+| 4 | fourth | 2 |
+| 5 | ⵜⴰⴱⵔⵓⵙⵉⵜ | 2 |
+| 6 | ⵜⴰⵙⵏⴽⵜⴰ | 2 |
+| 7 | ⵜⵉⵣⵎⵣⴰⵏⵉⵏ | 2 |
+| 8 | ⵜⴰⴷⵓⵥⴽⵉⵡⵜ | 2 |
+| 9 | ⴰⵎⵥⵕⴷⴳⴰⵔ | 2 |
+| 10 | ⵜⴰⵥⵕⵎⴰⵔⴽⵙⵉⵜ | 2 |
+
+### Zipf's Law Analysis
+
+| Metric | Value |
+|--------|-------|
+| Zipf Coefficient | 1.2553 |
+| R² (Goodness of Fit) | 0.991414 |
+| Adherence Quality | **excellent** |
+
+### Coverage Analysis
+
+| Top N Words | Coverage |
+|-------------|----------|
+| Top 100 | 67.5% |
+| Top 1,000 | 88.5% |
+| Top 5,000 | 94.6% |
+| Top 10,000 | 96.7% |
+
+### Key Findings
+
+- **Zipf Compliance:** R²=0.9914 indicates excellent adherence to Zipf's law
+- **High Frequency Dominance:** Top 100 words cover 67.5% of corpus
+- **Long Tail:** 25,191 words needed for remaining 3.3% 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 | 0.7259 🏆 | 0.3600 | N/A | N/A |
+| **mono_64d** | 64 | 0.5835 | 0.3114 | N/A | N/A |
+| **mono_128d** | 128 | 0.1766 | 0.3125 | N/A | N/A |
+| **aligned_32d** | 32 | 0.7259 | 0.3745 | 0.0080 | 0.0540 |
+| **aligned_64d** | 64 | 0.5835 | 0.3265 | 0.0120 | 0.1240 |
+| **aligned_128d** | 128 | 0.1766 | 0.3192 | 0.0360 | 0.1480 |
+
+### Key Findings
+
+- **Best Isotropy:** mono_32d with 0.7259 (more uniform distribution)
+- **Semantic Density:** Average pairwise similarity of 0.3340. Lower values indicate better semantic separation.
+- **Alignment Quality:** Aligned models achieve up to 3.6% 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 | **0.001** | Low formulaic 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 |
+|--------|----------|
+| `-ⵜ` | ⵜⵉⵎⵙⵙⵉ, ⵜⴳⵎⴰⵎⵜ, ⵜⵛⴰⵡⵉⵜ |
+| `-ⵜⴰ` | ⵜⴰⵎⴰⴽⵓⴷⵜ, ⵜⴰⴱⵕⵕⴰⵏⵉⵢⵜ, ⵜⴰⵇⵇⴰⵢⵜ |
+| `-ⵉ` | ⵉⵙⵙⵏⵄⴰⵜ, ⵉⴳⵯⵔⵔⴰⵎⵏ, ⵉⵊ |
+| `-ⴰ` | ⴰⵎⵙⵏⴽⴰⵔ, ⴰⵜⵉⵍⵉⴼⵉⵣⵢⵓⵏ, ⴰⵎⵖⵔⵉⴱⵉⵢ |
+| `-ⵓ` | ⵓⵊⵔⵉ, ⵓⴳⵜⴷⵉⵙ, ⵓⵔⵔⴰⵡ |
+| `-ⵜⵉ` | ⵜⵉⵎⵙⵙⵉ, ⵜⵉⵎⵥⴰⵕⵕⵓⵕⵉⵏ, ⵜⵉⵎⵥⵍⴰⵢⵉⵏ |
+| `-ⵍ` | ⵍⵃⵓⵎⴰ, ⵍⵡⴰⴷ, ⵍⴳⵯⵍⵍⴰ |
+| `-ⵉⵎ` | ⵉⵎⵥⵉⵏⵛⵓⵜⴰⵏⴱⵉⵔ, ⵉⵎⵢⴰⴳⴰⵔ, ⵉⵎⴷⴰⵏ |
+
+#### Productive Suffixes
+| Suffix | Examples |
+|--------|----------|
+| `-ⵏ` | ⴽⵔⵓⵛⵏ, ⵉⴳⵯⵔⵔⴰⵎⵏ, ⵜⵉⵎⵥⴰⵕⵕⵓⵕⵉⵏ |
+| `-ⵜ` | ⵜⴳⵎⴰⵎⵜ, ⵜⵛⴰⵡⵉⵜ, ⵉⵙⵙⵏⵄⴰⵜ |
+| `-ⵉⵏ` | ⵜⵉⵎⵥⴰⵕⵕⵓⵕⵉⵏ, ⵣⵣⵏⵣⴰⵏⵉⵏ, ⵜⵉⵎⵥⵍⴰⵢⵉⵏ |
+| `-ⴰ` | ⴱⵓⴷⴰ, ⵊⴰⵎⴰⵢⴽⴰ, ⵍⵃⵓⵎⴰ |
+| `-ⵉ` | ⵜⵉⵎⵙⵙⵉ, ⵓⵊⵔⵉ, ⵏⵜⵜⵉⵏⵉ |
+| `-ⴰⵏ` | ⵉⴱⵇⵇⴰⵏ, ⵎⵛⴰⵛⴽⴰⵏ, ⵉⵎⴷⴰⵏ |
+| `-ⵉⵜ` | ⵜⵛⴰⵡⵉⵜ, ⵜⴰⴷⵉⵏⴰⵎⵉⵜ, ⴱⵓⵜⵓⵏⴼⵉⵜ |
+| `-ⵔ` | ⴰⵎⵙⵏⴽⴰⵔ, ⵜⵜⵔ, ⵉⵎⵥⵉⵏⵛⵓⵜⴰⵏⴱⵉⵔ |
+
+### 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 |
+|------|----------|------------------|----------|
+| `ⴰⴷⴷⴰ` | 1.60x | 54 contexts | ⵜⴰⴷⴷⴰ, ⴰⴷⴷⴰⴳ, ⵢⴰⴷⴷⴰ |
+| `ⵡⵓⵔⵉ` | 1.73x | 38 contexts | ⵜⵡⵓⵔⵉ, ⵜⵙⵡⵓⵔⵉ, ⴰⵙⵡⵓⵔⵉ |
+| `ⴳⴳⴰⵔ` | 1.70x | 24 contexts | ⵉⴳⴳⴰⵔ, ⴳⴳⴰⵔⵏ, ⵓⴳⴳⴰⵔ |
+| `ⵓⴳⴳⴰ` | 1.65x | 24 contexts | ⵢⵓⴳⴳⴰ, ⵜⵓⴳⴳⴰ, ⵓⴳⴳⴰⵏ |
+| `ⵜⵜⴰⵢ` | 1.71x | 19 contexts | ⴰⵜⵜⴰⵢ, ⵓⵡⵜⵜⴰⵢ, ⵓⵏⵜⵜⴰⵢ |
+| `ⴰⵜⵜⴰ` | 1.62x | 22 contexts | ⴰⵜⵜⴰⵢ, ⵎⴰⵜⵜⴰ, ⴰⵜⵜⴰⵖ |
+| `ⵎⵉⵔⵉ` | 1.54x | 21 contexts | ⵉⵎⵉⵔⵉ, ⵓⵎⵉⵔⵉⴳ, ⵜⵎⵉⵔⵉⵜ |
+| `ⴷⴷⴰⴷ` | 1.66x | 16 contexts | ⵃⴷⴷⴰⴷ, ⵓⴷⴷⴰⴷ, ⵉⴷⴷⴰⴷ |
+| `ⴰⵎⴰⵜ` | 1.50x | 17 contexts | ⴰⵎⴰⵜⵓ, ⴰⵎⴰⵜⴰ, ⴰⵎⴰⵜⵜⵓ |
+| `ⵙⵍⵎⴷ` | 1.69x | 12 contexts | ⴰⵙⵍⵎⴷ, ⵓⵙⵍⵎⴷ, ⵙⵍⵎⴷⵏ |
+| `ⵉⵔⵉⵜ` | 1.59x | 14 contexts | ⵜⵉⵔⵉⵜ, ⵙⵉⵔⵉⵜ, ⵙⴱⵉⵔⵉⵜ |
+| `ⴰⵢⵉⵏ` | 1.86x | 9 contexts | ⴼⵍⴰⵢⵉⵏ, ⵜⵎⴷⴰⵢⵉⵏ, ⵜⵓⵎⴰⵢⵉⵏ |
+
+### 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 |
+|--------|--------|-----------|----------|
+| `-ⵜ` | `-ⵜ` | 684 words | ⵜⴰⴱⵔⵓⵜⵉⵙⵜⴰⵏⵜⵉⵜ, ⵜⴰⵏⵓⵍⴼⵓⵜ |
+| `-ⵉ` | `-ⵏ` | 523 words | ⵉⴼⵓⵄⵣⵏ, ⵉⵎⵙⴷⵎⴰⵔⵏ |
+| `-ⵜ` | `-ⵏ` | 379 words | ⵜⵢⴰⴼⵓⵜⵉⵏ, ⵜⵉⵕⵚⵍⵉⵢⵉⵏ |
+| `-ⵜ` | `-ⵉⵏ` | 331 words | ⵜⵢⴰⴼⵓⵜⵉⵏ, ⵜⵉⵕⵚⵍⵉⵢⵉⵏ |
+| `-ⵜ` | `-ⵉⵜ` | 130 words | ⵜⴰⴱⵔⵓⵜⵉⵙⵜⴰⵏⵜⵉⵜ, ⵜⴰⵊⵓⴳⵕⴰⴼⵉⵜ |
+| `-ⵍ` | `-ⴰ` | 101 words | ⵍⴼⴰⵢⴹⴰ, ⵍⴱⵕⵕⴰⵏⵢⵢⴰ |
+| `-ⵜ` | `-ⴰ` | 74 words | ⵜⵜⵓⴱⵏⴰ, ⵜⴰⵎⴰ |
+| `-ⵉ` | `-ⴰⵏ` | 63 words | ⵉⵎⵛⴰⵛⴽⴰⵏ, ⵉⵡⴷⴰⵏ |
+| `-ⴰ` | `-ⵏ` | 58 words | ⴰⵀⵉⵍⵏ, ⴰⵎⴽⴰⵏ |
+| `-ⴰ` | `-ⵉ` | 47 words | ⴰⵎⵣⴳⵉ, ⴰⴷⵡⴰⵍⵉ |
+
+### 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 |
+|------|-----------------|------------|------|
+| ⵜⵉⵔⵍⵓⴳⵏⴰⵏⵉⵏ | **`ⵜⵉⵔⵍⵓⴳⵏⴰ-ⵏ-ⵉⵏ`** | 7.5 | `ⵏ` |
+| ⵜⴳⵔⴰⵖⵍⴰⵏⵉⵏ | **`ⵜⴳⵔⴰⵖⵍⴰ-ⵏ-ⵉⵏ`** | 7.5 | `ⵏ` |
+| ⵜⵜⵄⵕⵕⴱⵏⵉⵏ | **`ⵜⵜⵄⵕⵕⴱ-ⵏ-ⵉⵏ`** | 7.5 | `ⵏ` |
+| ⵉⵜⵜⴰⵡⵙⵙⴰⵏⵏ | **`ⵉⵜⵜⴰⵡⵙⵙⴰ-ⵏ-ⵏ`** | 7.5 | `ⵏ` |
+| ⵉⵎⵖⵔⴰⴷⴰⵏⵏ | **`ⵉⵎⵖⵔⴰⴷⴰ-ⵏ-ⵏ`** | 7.5 | `ⵏ` |
+| ⵜⵉⵎⴰⵙⵉⵏⵉⵏ | **`ⵜⵉⵎⴰⵙ-ⵉⵏ-ⵉⵏ`** | 7.5 | `ⵉⵏ` |
+| ⵉⵙⵉⵏⴰⵔⵢⵓⵜⵏ | **`ⵉⵙⵉⵏⴰⵔⵢⵓ-ⵜ-ⵏ`** | 7.5 | `ⵜ` |
+| ⵜⵉⵙⵏⵛⵏⵢⴰⵍⴰⵏⵉⵏ | **`ⵜⵉⵙⵏⵛⵏⵢⴰⵍ-ⴰⵏ-ⵉⵏ`** | 7.5 | `ⴰⵏ` |
+| ⴽⵔⵉⵙⵜⵢⴰⵏⵓ | **`ⴽⵔⵉⵙⵜⵢⴰ-ⵏ-ⵓ`** | 7.5 | `ⵏ` |
+| ⵜⵜⵓⵙⵎⵔⴰⵙⵏⵉⵏ | **`ⵜⵜⵓⵙⵎⵔⴰⵙ-ⵏ-ⵉⵏ`** | 7.5 | `ⵏ` |
+| ⵜⵉⵎⵢⴰⵇⴰⵏⵉⵏ | **`ⵜⵉⵎⵢⴰⵇ-ⴰⵏ-ⵉⵏ`** | 7.5 | `ⴰⵏ` |
+| ⵜⵉⵏⵎⴹⴰⵏⵉⵏ | **`ⵜⵉⵏⵎⴹ-ⴰⵏ-ⵉⵏ`** | 7.5 | `ⴰⵏ` |
+| ⵜⵜⵡⴰⵙⵙⴰⵏⵏⵜ | **`ⵜⵜⵡⴰⵙⵙⴰⵏ-ⵏ-ⵜ`** | 7.5 | `ⵏ` |
+| ⵉⵙⵜⵓⴷⵢⵓⵜⵏ | **`ⵉⵙⵜⵓⴷⵢⵓ-ⵜ-ⵏ`** | 7.5 | `ⵜ` |
+| ⵉⵜⵜⵓⵙⵖⵥⵏⵏ | **`ⵉⵜⵜⵓⵙⵖⵥ-ⵏ-ⵏ`** | 7.5 | `ⵏ` |
+
+### 6.6 Linguistic Interpretation
+
+> **Automated Insight:**
+The language Standard Moroccan Tamazight shows high morphological productivity. The subword models are significantly more efficient than word models, suggesting a rich system of affixation or compounding.
+
+---
+## 7. Summary & Recommendations
+
+![Performance Dashboard](visualizations/performance_dashboard.png)
+
+### Production Recommendations
+
+| Component | Recommended | Rationale |
+|-----------|-------------|-----------|
+| Tokenizer | **64k BPE** | Best compression (3.84x) |
+| N-gram | **2-gram** | Lowest perplexity (278) |
+| Markov | **Context-4** | Highest predictability (95.5%) |
+| 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 |
+
+---
+## 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.
+
+### Project
+
+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)
+
+### 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},
+  publisher = {Zenodo},
+  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)
+- 🤝 Sponsor: [Featherless AI](https://featherless.ai)
+---
+*Generated by Wikilangs Models Pipeline*
+
+*Report Date: 2026-01-11 05:56:32*

models/embeddings/aligned/zgh_128d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f416db87f7f77dc715a240c5b5550eaa821ce66371230381cb1814121a0bddd
+size 1043572275

models/embeddings/aligned/zgh_128d.meta.json

@@ -0,0 +1 @@
+{"lang": "zgh", "dim": 128, "max_seq_len": 512, "is_aligned": true}

models/embeddings/aligned/zgh_128d.projection.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0de516e2e2b39c6c85ed1e729a08e17e065eba6002e9b0d81ae1d10e90a04829
+size 65664

models/embeddings/aligned/zgh_128d_metadata.json

@@ -0,0 +1,8 @@
+{
+  "language": "zgh",
+  "dimension": 128,
+  "version": "aligned",
+  "hub_language": "en",
+  "seed_vocab_size": 3830,
+  "vocab_size": 18693
+}

models/embeddings/aligned/zgh_32d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f1abb279576d8a8c84dc385e40331e9ee54159a6976ac7e153cb82d5a654a0c
+size 261216051

models/embeddings/aligned/zgh_32d.meta.json

@@ -0,0 +1 @@
+{"lang": "zgh", "dim": 32, "max_seq_len": 512, "is_aligned": true}

models/embeddings/aligned/zgh_32d.projection.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3ab41e725556a9489a2b21d0b2021b0229f511b5bb8f0a1ea61b31af9f53c1c
+size 4224

models/embeddings/aligned/zgh_32d_metadata.json

@@ -0,0 +1,8 @@
+{
+  "language": "zgh",
+  "dimension": 32,
+  "version": "aligned",
+  "hub_language": "en",
+  "seed_vocab_size": 3830,
+  "vocab_size": 18693
+}

models/embeddings/aligned/zgh_64d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881de8d18c85ed086519dd912104a8310075bf6deea4b488e0e4a8dddfa6fa4f
+size 522001459

models/embeddings/aligned/zgh_64d.meta.json

@@ -0,0 +1 @@
+{"lang": "zgh", "dim": 64, "max_seq_len": 512, "is_aligned": true}

models/embeddings/aligned/zgh_64d.projection.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3d16c88653a4dd058c46c9c075d15aebade42cd37bf313ba62ee3f9621f4877
+size 16512

models/embeddings/aligned/zgh_64d_metadata.json

@@ -0,0 +1,8 @@
+{
+  "language": "zgh",
+  "dimension": 64,
+  "version": "aligned",
+  "hub_language": "en",
+  "seed_vocab_size": 3830,
+  "vocab_size": 18693
+}

models/embeddings/monolingual/zgh_128d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f416db87f7f77dc715a240c5b5550eaa821ce66371230381cb1814121a0bddd
+size 1043572275

models/embeddings/monolingual/zgh_128d.meta.json

@@ -0,0 +1 @@
+{"lang": "zgh", "dim": 128, "max_seq_len": 512, "is_aligned": false}

models/embeddings/monolingual/zgh_128d_metadata.json

@@ -0,0 +1,16 @@
+{
+  "language": "zgh",
+  "dimension": 128,
+  "version": "monolingual",
+  "training_params": {
+    "algorithm": "skipgram",
+    "min_count": 5,
+    "window": 5,
+    "negative": 5,
+    "epochs": 5,
+    "encoding_method": "rope",
+    "dim": 128,
+    "threads": 5
+  },
+  "vocab_size": 18693
+}

models/embeddings/monolingual/zgh_32d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f1abb279576d8a8c84dc385e40331e9ee54159a6976ac7e153cb82d5a654a0c
+size 261216051

models/embeddings/monolingual/zgh_32d.meta.json

@@ -0,0 +1 @@
+{"lang": "zgh", "dim": 32, "max_seq_len": 512, "is_aligned": false}

models/embeddings/monolingual/zgh_32d_metadata.json

@@ -0,0 +1,16 @@
+{
+  "language": "zgh",
+  "dimension": 32,
+  "version": "monolingual",
+  "training_params": {
+    "algorithm": "skipgram",
+    "min_count": 5,
+    "window": 5,
+    "negative": 5,
+    "epochs": 5,
+    "encoding_method": "rope",
+    "dim": 32,
+    "threads": 5
+  },
+  "vocab_size": 18693
+}

models/embeddings/monolingual/zgh_64d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881de8d18c85ed086519dd912104a8310075bf6deea4b488e0e4a8dddfa6fa4f
+size 522001459

models/embeddings/monolingual/zgh_64d.meta.json

@@ -0,0 +1 @@
+{"lang": "zgh", "dim": 64, "max_seq_len": 512, "is_aligned": false}

models/embeddings/monolingual/zgh_64d_metadata.json

@@ -0,0 +1,16 @@
+{
+  "language": "zgh",
+  "dimension": 64,
+  "version": "monolingual",
+  "training_params": {
+    "algorithm": "skipgram",
+    "min_count": 5,
+    "window": 5,
+    "negative": 5,
+    "epochs": 5,
+    "encoding_method": "rope",
+    "dim": 64,
+    "threads": 5
+  },
+  "vocab_size": 18693
+}

models/subword_markov/zgh_markov_ctx1_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:938c28b7d81d02e47bd702e6b2089e992460e15d177630dbc199864e688715d1
+size 79856

models/subword_markov/zgh_markov_ctx1_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 1,
+  "variant": "subword",
+  "language": "zgh",
+  "unique_contexts": 1091,
+  "total_transitions": 12568198
+}

models/subword_markov/zgh_markov_ctx2_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74530b8835b96c24eaacd595c75833088aa5f40a8fb44ab5f1c940312c72d29a
+size 479866

models/subword_markov/zgh_markov_ctx2_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 2,
+  "variant": "subword",
+  "language": "zgh",
+  "unique_contexts": 9682,
+  "total_transitions": 12556423
+}

models/subword_markov/zgh_markov_ctx3_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7434a064c397868bcea3b0020d7cb874b50d0ae8f56fa4643e3f1d22d7da5d1a
+size 1784932

models/subword_markov/zgh_markov_ctx3_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 3,
+  "variant": "subword",
+  "language": "zgh",
+  "unique_contexts": 59433,
+  "total_transitions": 12544648
+}

models/subword_markov/zgh_markov_ctx4_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:804ce610c67291ad96267caaec09ad56e3868fb08b2d2929d8f7238c4059eb18
+size 4966835

models/subword_markov/zgh_markov_ctx4_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 4,
+  "variant": "subword",
+  "language": "zgh",
+  "unique_contexts": 223378,
+  "total_transitions": 12532873
+}

models/subword_ngram/zgh_2gram_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30a8654d0166d09284b02456cd1dfbeddee6abde455db8e7a9e30c0e99ce4c8f
+size 56928

models/subword_ngram/zgh_2gram_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 2,
+  "variant": "subword",
+  "language": "zgh",
+  "unique_ngrams": 3951,
+  "total_ngrams": 12568198
+}

models/subword_ngram/zgh_3gram_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:480fd64a8e67c3ea7beee9dfcdef755092cf96ae6c6c1cff283995d7cd76ad31
+size 416124

models/subword_ngram/zgh_3gram_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 3,
+  "variant": "subword",
+  "language": "zgh",
+  "unique_ngrams": 30764,
+  "total_ngrams": 12556423
+}

models/subword_ngram/zgh_4gram_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0003430af7f59c00343cee89fb66d8230a2133f3cd6a23237a8f02f5584042c6
+size 1604025

models/subword_ngram/zgh_4gram_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 4,
+  "variant": "subword",
+  "language": "zgh",
+  "unique_ngrams": 123122,
+  "total_ngrams": 12544648
+}

models/subword_ngram/zgh_5gram_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:300e5b2271d12fe4c1adb23e7ffed07f3529f0f81424c94e0081a47ec3282fa1
+size 3471121

models/subword_ngram/zgh_5gram_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 5,
+  "variant": "subword",
+  "language": "zgh",
+  "unique_ngrams": 251758,
+  "total_ngrams": 12532873
+}

models/tokenizer/zgh_tokenizer_16k.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:856e0b0a254c13305a02628ae57161ecfdb34ac362258f963e33edc29390a105
+size 616483

models/tokenizer/zgh_tokenizer_32k.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8cc7e8cde95ab83cecb3e1c2ad1f325e813ade9c670aa200d5f9ec16e16575e
+size 1002511

models/tokenizer/zgh_tokenizer_64k.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38a4d62483923a484dc26acd2a78ab742bb2f0489144ae59bb168fe7eee57ab3
+size 1826225

models/tokenizer/zgh_tokenizer_8k.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67859e798567500b2d73db14bf95f83f54be20de8858cc0c8c84ffba5fc7675d
+size 424656

models/vocabulary/zgh_vocabulary.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b70e08184971d018a61e303ca3ddd9183488ec6af26b80124432d0de0ee0533e
+size 659246

models/vocabulary/zgh_vocabulary_metadata.json

@@ -0,0 +1,17 @@
+{
+  "language": "zgh",
+  "vocabulary_size": 35191,
+  "variant": "full",
+  "statistics": {
+    "type_token_ratio": 0.03358929904433284,
+    "coverage": {
+      "top_100": 0.6615755824762495,
+      "top_1000": 0.8681169642716713,
+      "top_5000": 0.9274460009945036,
+      "top_10000": 0.9481434521051335
+    },
+    "hapax_count": 48098,
+    "hapax_ratio": 0.5774832210736112,
+    "total_documents": 11775
+  }
+}

models/word_markov/zgh_markov_ctx1_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe0a484185a6a24636abdb1fd92fadd8f0bbb430c96ad20f8fb13bedd8e59ec8
+size 4014067