Upload all models and assets for bo (20251001)

README.md

@@ -23,14 +23,14 @@ dataset_info:
 metrics:
   - name: best_compression_ratio
     type: compression
-    value: 5.961
+    value: 5.300
   - name: best_isotropy
     type: isotropy
-    value: 0.7739
+    value: 0.8494
   - name: vocabulary_size
     type: vocab
-    value: 13016
-generated: 2025-12-28
+    value: 0
+generated: 2026-01-03
 ---
 
 # BO - Wikilangs Models
@@ -44,12 +44,13 @@ We analyze tokenizers, n-gram models, Markov chains, vocabulary statistics, and
 ### Models & Assets
 
 - Tokenizers (8k, 16k, 32k, 64k)
-- N-gram models (2, 3, 4-gram)
-- Markov chains (context of 1, 2, 3 and 4)
+- 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
+- Embeddings in various sizes and dimensions (aligned and unaligned)
 - Language Vocabulary
 - Language Statistics
+
 ![Performance Dashboard](visualizations/performance_dashboard.png)
 
 ### Analysis and Evaluation
@@ -59,7 +60,8 @@ We analyze tokenizers, n-gram models, Markov chains, vocabulary statistics, and
 - [3. Markov Chain Evaluation](#3-markov-chain-evaluation)
 - [4. Vocabulary Analysis](#4-vocabulary-analysis)
 - [5. Word Embeddings Evaluation](#5-word-embeddings-evaluation)
-- [6. Summary & Recommendations](#6-summary--recommendations)
+- [6. Morphological Analysis (Experimental)](#6-morphological-analysis)
+- [7. Summary & Recommendations](#7-summary--recommendations)
 - [Metrics Glossary](#appendix-metrics-glossary--interpretation-guide)
 - [Visualizations Index](#visualizations-index)
 
@@ -68,53 +70,57 @@ We analyze tokenizers, n-gram models, Markov chains, vocabulary statistics, and
 
 ![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** | 4.296x | 4.23 | 0.3002% | 389,363 |
-| **16k** | 4.846x | 4.77 | 0.3387% | 345,182 |
-| **32k** | 5.407x | 5.33 | 0.3779% | 309,326 |
-| **64k** | 5.961x 🏆 | 5.87 | 0.4166% | 280,591 |
+| **8k** | 4.065x | 4.07 | 0.3680% | 234,234 |
+| **16k** | 4.561x | 4.56 | 0.4129% | 208,750 |
+| **32k** | 4.981x | 4.98 | 0.4510% | 191,137 |
+| **64k** | 5.300x 🏆 | 5.30 | 0.4798% | 179,650 |
 
 ### Tokenization Examples
 
 Below are sample sentences tokenized with each vocabulary size:
 
-**Sample 1:** `གསལ་བྱེད་སུམ་ཅུའི་ནང་ནས་ཀ་ག་བ་ཟ་ར་ས་དྲུག་ནི་ལ་བཏགས་ཅན་གྱི་ཡི་གེ་དྲུག་གོ།
-༼དུང་དཀ...`
+**Sample 1:** `ཞེ་ཆེན་དགོན་ནི་ཞེ་ཆེན་རབ་འབྱམས་དང་པོ་བསྟན་པའི་རྒྱལ་མཚན་གྱིས་ཕྱག་བཏབ་པ་ཡིན།`
 
 | Vocab | Tokens | Count |
 |-------|--------|-------|
-| 8k | `▁གས ལ་བྱེད་ སུམ་ ཅུའི་ ནང་ནས་ ཀ་ ག ་བ་ ཟ་ ར་ ... (+16 more)` | 26 |
-| 16k | `▁གསལ་བྱེད་ སུམ་ཅུའི་ ནང་ནས་ ཀ་ ག ་བ་ ཟ་ ར་ ས་ དྲུག་ ... (+13 more)` | 23 |
-| 32k | `▁གསལ་བྱེད་ སུམ་ཅུའི་ ནང་ནས་ ཀ་ ག་བ་ ཟ་ ར་ས་ དྲུག་ནི་ ལ་བཏགས་ ཅན་གྱི་ ... (+9 more)` | 19 |
-| 64k | `▁གསལ་བྱེད་ སུམ་ཅུའི་ ནང་ནས་ ཀ་ ག་བ་ ཟ་ ར་ས་ དྲུག་ནི་ ལ་བཏགས་ ཅན་གྱི་ ... (+9 more)` | 19 |
+| 8k | `▁ཞེ་ ཆེན་ དགོན་ ནི་ ཞེ་ ཆེན་ རབ་འབྱམས་ དང་པོ་ བསྟན་པའི་ རྒྱལ་མཚན་ ... (+3 more)` | 13 |
+| 16k | `▁ཞེ་ ཆེན་ དགོན་ནི་ ཞེ་ ཆེན་ རབ་འབྱམས་ དང་པོ་ བསྟན་པའི་ རྒྱལ་མཚན་གྱིས་ ཕྱག་བཏབ་ ... (+1 more)` | 11 |
+| 32k | `▁ཞེ་ཆེན་ དགོན་ནི་ ཞེ་ཆེན་ རབ་འབྱམས་ དང་པོ་ བསྟན་པའི་ རྒྱལ་མཚན་གྱིས་ ཕྱག་བཏབ་ པ་ཡིན།` | 9 |
+| 64k | `▁ཞེ་ཆེན་ དགོན་ནི་ ཞེ་ཆེན་ རབ་འབྱམས་ དང་པོ་ བསྟན་པའི་ རྒྱལ་མཚན་གྱིས་ ཕྱག་བཏབ་ པ་ཡིན།` | 9 |
 
-**Sample 2:** `བདག་སློབ་བུས་ལུས་ངག་ཡིད་གསུམ་ཁྱོད་ལ་དུས་བརྟན་དུ་འབུལ།   ང་ཚོ་མྱུར་དུ་མཇལ་འཛོམ་ཡ��...`
+**Sample 2:** `རང་གི་ཕ་མའི་ཁྱིམ་དུ་འཚོ་བ་སྐྱེལ་བའི་ཞེ་སའི་ཚིག ༼དུང་དཀར་ཚིག་མཛོད་ཆེན་མོ་༽ནས་བཏུས...`
 
 | Vocab | Tokens | Count |
 |-------|--------|-------|
-| 8k | `▁བདག་ སློབ་བ ུས་ ལུས་ ངག་ཡིད་ གསུམ་ ཁྱོད་ལ་ དུས་ བརྟན་ དུ་ ... (+18 more)` | 28 |
-| 16k | `▁བདག་ སློབ་བ ུས་ ལུས་ངག་ཡིད་ གསུམ་ ཁྱོད་ལ་ དུས་ བརྟན་ དུ་ འབུལ། ... (+13 more)` | 23 |
-| 32k | `▁བདག་ སློབ་བ ུས་ ལུས་ངག་ཡིད་གསུམ་ ཁྱོད་ལ་ དུས་ བརྟན་ དུ་ འབུལ། ▁ང་ཚོ་ ... (+12 more)` | 22 |
-| 64k | `▁བདག་ སློབ་བ ུས་ ལུས་ངག་ཡིད་གསུམ་ ཁྱོད་ལ་ དུས་ བརྟན་ དུ་ འབུལ། ▁ང་ཚོ་ ... (+10 more)` | 20 |
+| 8k | `▁རང་གི་ ཕ ་མའི་ ཁྱིམ་ དུ་ འཚོ་བ་ སྐྱ ེལ་བའི་ ཞེ་ སའི་ ... (+4 more)` | 14 |
+| 16k | `▁རང་གི་ ཕ་མའི་ ཁྱིམ་དུ་ འཚོ་བ་ སྐྱ ེལ་བའི་ ཞེ་སའི་ ཚིག ▁༼དུང་ དཀར་ཚིག་མཛོད་ ... (+1 more)` | 11 |
+| 32k | `▁རང་གི་ ཕ་མའི་ ཁྱིམ་དུ་ འཚོ་བ་ སྐྱེལ་བའི་ ཞེ་སའི་ཚིག ▁༼དུང་ དཀར་ཚིག་མཛོད་ ཆེན་མོ་༽ནས་བཏུས།` | 9 |
+| 64k | `▁རང་གི་ཕ་མའི་ ཁྱིམ་དུ་ འཚོ་བ་སྐྱེལ་བའི་ ཞེ་སའི་ཚིག ▁༼དུང་ དཀར་ཚིག་མཛོད་ ཆེན་མོ་༽ནས་བཏུས།` | 7 |
 
-**Sample 3:** `མི་འཁྲུགས་པ་སྐྱབས་སྦྱིན་ཅན།   
-དེང་སང་ཇོ་བོ་རིན་པོ་ཆེའི་སྐུ་རྒྱབ་ཏུ་བཞུགས་པའི་ཇོ...`
+**Sample 3:** `དུས་རྟག་ཏུ་སྐྱེ་འཇིག་མི་བྱེད་པ། དཔེར་ན། ནམ་མཁའ་ལྟ་བུ།`
 
 | Vocab | Tokens | Count |
 |-------|--------|-------|
-| 8k | `▁མི་ འཁྲུགས་ པ་ སྐྱབས་ སྦྱིན་ ཅན། ▁དེང་སང་ ཇོ་བོ་ རིན་པོ་ཆེའི་ སྐུ་ ... (+12 more)` | 22 |
-| 16k | `▁མི་ འཁྲུགས་ པ་ སྐྱབས་ སྦྱིན་ ཅན། ▁དེང་སང་ ཇོ་བོ་ རིན་པོ་ཆེའི་ སྐུ་ ... (+11 more)` | 21 |
-| 32k | `▁མི་ འཁྲུགས་པ་ སྐྱབས་ སྦྱིན་ ཅན། ▁དེང་སང་ ཇོ་བོ་ རིན་པོ་ཆེའི་ སྐུ་ རྒྱབ་ཏུ་བ ... (+7 more)` | 17 |
-| 64k | `▁མི་ འཁྲུགས་པ་ སྐྱབས་སྦྱིན་ ཅན། ▁དེང་སང་ ཇོ་བོ་ རིན་པོ་ཆེའི་སྐུ་ རྒྱབ་ཏུ་བ ཞུགས་པའི་ ཇོ་བོ་ ... (+5 more)` | 15 |
+| 8k | `▁དུས་ རྟག་ཏུ་ སྐྱེ་ འཇིག་ མི་ བྱེད་པ། ▁དཔེར་ན། ▁ནམ་མཁའ་ ལྟ་བུ།` | 9 |
+| 16k | `▁དུས་ རྟག་ཏུ་ སྐྱེ་ འཇིག་ མི་ བྱེད་པ། ▁དཔེར་ན། ▁ནམ་མཁའ་ ལྟ་བུ།` | 9 |
+| 32k | `▁དུས་ རྟག་ཏུ་ སྐྱེ་འཇིག་ མི་ བྱེད་པ། ▁དཔེར་ན། ▁ནམ་མཁའ་ ལྟ་བུ།` | 8 |
+| 64k | `▁དུས་རྟག་ཏུ་ སྐྱེ་འཇིག་ མི་བྱེད་པ། ▁དཔེར་ན། ▁ནམ་མཁའ་ ལྟ་བུ།` | 6 |
 
 
 ### Key Findings
 
-- **Best Compression:** 64k achieves 5.961x compression
-- **Lowest UNK Rate:** 8k with 0.3002% unknown tokens
+- **Best Compression:** 64k achieves 5.300x compression
+- **Lowest UNK Rate:** 8k with 0.3680% unknown tokens
 - **Trade-off:** Larger vocabularies improve compression but increase model size
 - **Recommendation:** 32k vocabulary provides optimal balance for production use
 
@@ -123,57 +129,89 @@ Below are sample sentences tokenized with each vocabulary size:
 
 ![N-gram Perplexity](visualizations/ngram_perplexity.png)
 
+![N-gram Unique](visualizations/ngram_unique.png)
+
 ![N-gram Coverage](visualizations/ngram_coverage.png)
 
 ### Results
 
-| N-gram | Perplexity | Entropy | Unique N-grams | Top-100 Coverage | Top-1000 Coverage |
-|--------|------------|---------|----------------|------------------|-------------------|
-| **2-gram** | 397 🏆 | 8.63 | 16,730 | 60.3% | 96.5% |
-| **2-gram** | 259 🏆 | 8.02 | 10,716 | 68.5% | 98.4% |
-| **3-gram** | 2,660 | 11.38 | 107,789 | 28.7% | 70.8% |
-| **3-gram** | 1,576 | 10.62 | 61,755 | 31.0% | 81.3% |
-| **4-gram** | 14,448 | 13.82 | 410,390 | 13.4% | 41.2% |
-| **4-gram** | 7,647 | 12.90 | 237,121 | 14.5% | 47.5% |
+| N-gram | Variant | Perplexity | Entropy | Unique N-grams | Top-100 Coverage | Top-1000 Coverage |
+|--------|---------|------------|---------|----------------|------------------|-------------------|
+| **2-gram** | Word | 36,069 | 15.14 | 160,381 | 8.0% | 26.4% |
+| **2-gram** | Subword | 469 🏆 | 8.87 | 14,734 | 57.9% | 90.6% |
+| **3-gram** | Word | 207,650 | 17.66 | 482,234 | 3.8% | 11.0% |
+| **3-gram** | Subword | 3,733 | 11.87 | 86,351 | 25.0% | 62.7% |
+| **4-gram** | Word | 569,587 | 19.12 | 997,749 | 3.3% | 7.5% |
+| **4-gram** | Subword | 21,504 | 14.39 | 391,088 | 12.0% | 36.1% |
 
 ### Top 5 N-grams by Size
 
-**2-grams:**
+**2-grams (Word):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `པ དང` | 26,663 |
+| 2 | `པ ལ` | 12,165 |
+| 3 | `བ དང` | 12,147 |
+| 4 | `ཐམས ཅད` | 11,625 |
+| 5 | `པ ནི` | 10,955 |
+
+**3-grams (Word):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `སྤྱོད འཇུག གི` | 4,095 |
+| 2 | `ད དུང གཟིགས` | 3,422 |
+| 3 | `ཞེས བྱ བ` | 3,401 |
+| 4 | `ཕྱི ཕྱོགས དྲ` | 3,394 |
+| 5 | `ཕྱོགས དྲ མཐུད` | 3,394 |
+
+**4-grams (Word):**
 
 | Rank | N-gram | Count |
 |------|--------|-------|
-| 1 | `ི ་` | 1,330,962 |
-| 2 | `་ ས` | 923,359 |
-| 3 | `ན ་` | 864,506 |
-| 4 | `ས ་` | 804,391 |
-| 5 | `་ ར` | 740,793 |
+| 1 | `ཕྱི ཕྱོགས དྲ མཐུད` | 3,393 |
+| 2 | `དཔྱད གཞིའི དཀར ཆག` | 3,391 |
+| 3 | `ཟིན ཐོ འམ དཔྱད` | 2,805 |
+| 4 | `ཐོ འམ དཔྱད གཞི` | 2,802 |
+| 5 | `ད དུང གཟིགས ཕྱི` | 2,789 |
 
-**3-grams:**
+**2-grams (Subword):**
 
 | Rank | N-gram | Count |
 |------|--------|-------|
-| 1 | `་ པ ་` | 412,050 |
-| 2 | `ྱ ི ་` | 279,592 |
-| 3 | `ོ ད ་` | 249,936 |
-| 4 | `་ དང ་` | 232,586 |
-| 5 | `་ ཀ ྱ` | 225,678 |
+| 1 | `ས ་` | 1,063,653 |
+| 2 | `། _` | 775,741 |
+| 3 | `ང ་` | 696,058 |
+| 4 | `ན ་` | 582,326 |
+| 5 | `་ བ` | 571,331 |
 
-**4-grams:**
+**3-grams (Subword):**
 
 | Rank | N-gram | Count |
 |------|--------|-------|
-| 1 | `་ པའ ི ་` | 220,243 |
-| 2 | `་ ཀ ྱ ི` | 185,475 |
-| 3 | `་ ར ྒ ྱ` | 176,176 |
-| 4 | `ཀ ྱ ི ་` | 145,131 |
-| 5 | `་ ད ུ ་` | 133,021 |
+| 1 | `་ པ ་` | 222,811 |
+| 2 | `ག ས ་` | 205,307 |
+| 3 | `། _ །` | 180,441 |
+| 4 | `ས ་ པ` | 161,245 |
+| 5 | `་ ད ང` | 151,339 |
+
+**4-grams (Subword):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `་ ད ང ་` | 128,716 |
+| 2 | `་ པ འི ་` | 107,145 |
+| 3 | `ང ་ ། _` | 84,367 |
+| 4 | `ས ་ པ ་` | 74,777 |
+| 5 | `་ པ ར ་` | 62,788 |
 
 
 ### Key Findings
 
-- **Best Perplexity:** 2-gram with 259
+- **Best Perplexity:** 2-gram (subword) with 469
 - **Entropy Trend:** Decreases with larger n-grams (more predictable)
-- **Coverage:** Top-1000 patterns cover ~47% of corpus
+- **Coverage:** Top-1000 patterns cover ~36% of corpus
 - **Recommendation:** 4-gram or 5-gram for best predictive performance
 
 ---
@@ -181,55 +219,86 @@ Below are sample sentences tokenized with each vocabulary size:
 
 ![Markov Entropy](visualizations/markov_entropy.png)
 
+![Markov Contexts](visualizations/markov_contexts.png)
+
 ![Markov Branching](visualizations/markov_branching.png)
 
 ### Results
 
-| Context | Avg Entropy | Perplexity | Branching Factor | Unique Contexts | Predictability |
-|---------|-------------|------------|------------------|-----------------|----------------|
-| **1** | 0.2954 | 1.227 | 3.27 | 41,503 | 70.5% |
-| **1** | 1.4785 | 2.787 | 10.14 | 4,527 | 0.0% |
-| **2** | 0.2647 🏆 | 1.201 | 2.76 | 135,576 | 73.5% |
-| **2** | 0.6082 🏆 | 1.524 | 3.67 | 45,909 | 39.2% |
-| **3** | 0.2919 | 1.224 | 2.37 | 373,945 | 70.8% |
-| **3** | 0.5729 | 1.488 | 2.90 | 168,571 | 42.7% |
-| **4** | 0.3575 | 1.281 | 2.36 | 884,085 | 64.2% |
-| **4** | 0.4734 | 1.388 | 2.39 | 489,183 | 52.7% |
+| Context | Variant | Avg Entropy | Perplexity | Branching Factor | Unique Contexts | Predictability |
+|---------|---------|-------------|------------|------------------|-----------------|----------------|
+| **1** | Word | 0.9258 | 1.900 | 17.80 | 44,551 | 7.4% |
+| **1** | Subword | 0.8301 | 1.778 | 6.82 | 8,378 | 17.0% |
+| **2** | Word | 0.7004 | 1.625 | 3.77 | 792,341 | 30.0% |
+| **2** | Subword | 0.4672 | 1.382 | 4.10 | 57,113 | 53.3% |
+| **3** | Word | 0.2866 | 1.220 | 1.60 | 2,987,004 | 71.3% |
+| **3** | Subword | 0.4482 | 1.364 | 3.28 | 233,848 | 55.2% |
+| **4** | Word | 0.1070 🏆 | 1.077 | 1.17 | 4,767,837 | 89.3% |
+| **4** | Subword | 0.3731 | 1.295 | 2.37 | 765,950 | 62.7% |
+
+### Generated Text Samples (Word-based)
+
+Below are text samples generated from each word-based Markov chain model:
+
+**Context Size 1:**
+
+1. `པ ཐམས ཅད དུ བཅུག དེ བསིལ ཟེར མི བཏུབ པའི ཚུལ ཁྲིམས རྒྱལ པོ ཆེའི`
+2. `དང ཁ སྐོང ཝེར ཐུགས རྗེ གླུའི བསྟོད ས ལ བླ མའི སྲས འཇུག གི སྐད`
+3. `ལ བཙུན བསྟེན 2 5 ལོ རྒྱུས ས བཅད རྩོམ རིག སྔགས སོ ཁོས ང མ`
+
+**Context Size 2:**
+
+1. `པ དང ཉེ བའི མཆོད སྤྲིན རྣམ སྡུད དང ཞུས ཤིག བྱས བྱུང ༣༩ སྤྲིན པ བར`
+2. `པ ལ དབང ཐོབ ཤོག ཤུ དག ལི ཁྲིའི ཚོན གྱིས རབ མཛེས ཁ བའི གོས བཟང`
+3. `བ དང གཅོག པར བྱེད པ ཙམ ལ འཁྲུལ མིན རྨི སོགས རྣམ དབྱེ བཞི བའི དེ`
+
+**Context Size 3:**
+
+1. `སྤྱོད འཇུག གི རྣམ བཤད ཐེག ཆེན ཆོས ཀྱི རྒྱ མཚོ སོགས བྱོན རྒྱ དཀར ནག སེར དང`
+2. `ད དུང གཟིགས ཕྱི ཕྱོགས དྲ མཐུད དབྱིན ཇིའི རླུང འཕྲིན ཀུང སིས ཉིན དེར ཉིའུ གཡོད སྐབས`
+3. `ཞེས བྱ བ བསྲུང བའི དམ ཚིག ཅན ཐུགས དམ སྐུལ བ ནི འདི ལ རྟགས ངེས པ`
+
+**Context Size 4:**
+
+1. `དཔྱད གཞིའི དཀར ཆག ད དུང གཟིགས བཙན པོ རིམ བྱོན གྱི མཚན བྱང བྲག གདོང བཀྲས གླིང དབང`
+2. `ཟིན ཐོ འམ དཔྱད གཞི དཔྱད གཞིའི དཀར ཆག ད དུང གཟིགས ཕྱི ཕྱོགས དྲ མཐུད ཤིང འཛུགས དུས`
+3. `ཐོ འམ དཔྱད གཞི དཔྱད གཞིའི དཀར ཆག ད དུང གཟིགས ཕྱི ཕྱོགས དྲ མཐུད དབྱིན ཇིའི རླུང འཕྲིན`
+
 
-### Generated Text Samples
+### Generated Text Samples (Subword-based)
 
-Below are text samples generated from each Markov chain model:
+Below are text samples generated from each subword-based Markov chain model:
 
 **Context Size 1:**
 
-1. `་ བ ། ཉམས ་ ན ་ འག ྲ ག ་ མ ་ ཤ ུ ང`
-2. `ི ར ྐ ྱ ན ་ བས ྒ ྲ ི ་ ད ་ མ ་ གཅ`
-3. `ོ ས ྙ ི ་ དང ་ ས ྲ ི ས ་ ཆ ུ ར ུ`
+1. `་ཁྲགཟུང་སྒྲིག་ཐུགནསལ་གྱུ`
+2. `ས་ན་པོ།_ལྷན་ཚད་གན་`
+3. `གཞིགས་བ་དྷྱ་བས་སྦྱིན།_`
 
 **Context Size 2:**
 
-1. `ི ་ ས ྒ ྲ ོ ད [ ང ] པའ ི ་ དཀར ་ ཡ ི`
-2. `་ ས ླ ོ ང ་ ག ྱ ི ས ་ འབ ྱ ོ ན ་ བཅས`
-3. `ན ་ ཆ ོ ས ་ རབ ་ འབ ྱ ུ ར ། ། ཁ ོ ངས`
+1. `ས་ལ་པའི་ཐུགས་ནག་འབྱོར`
+2. `།_རབས་ཀྱིས་དཀྱིལ་སྣང་གི`
+3. `ང་མ་བུདྡྷ་ཀྵེ་ཙཱ་བར་ནས།`
 
 **Context Size 3:**
 
-1. `་ པ ་ ཆ ུ བ ་ བ ྱ ེ ད ། ། ཁ ྲ ་ བ ྱ`
-2. `ྱ ི ་ ཕ ་ ར ོ ལ ་ ར ླ བས ་ ཀ ྱ ི ་ ར`
-3. `ོ ད ་ ཀ ྱ ི ས ་ བད ུ ན ་ ཅ ི ་ མ ི ན`
+1. `་པ་སྟེ།_ལྷ་ལྡན་ཡོང་ཡེ་ཤེས`
+2. `གས་མད་ོ_འགྱུར་རྡོ་རྗེའི་བསྲུ`
+3. `།_།རྣམ་འཆོར་བ་དང་སེམས`
 
 **Context Size 4:**
 
-1. `་ པའ ི ་ ར ྒ ྱ ར ་ བར ་ དཀའ ་ བའ ི ་ འཕ ྲ ུ`
-2. `་ ཀ ྱ ི ་ ནང ་ ག ི ་ འབ ུ མ ་ ཡང ་ ། ། ཤ`
-3. `་ ར ྒ ྱ ུ ད ་ པ ། ད ེ ་ ས ྟ ེ ། བ ྲ མ`
+1. `་དང་ཕྱོགས་སུ་བཞིན་ཉུལ་ཆོས`
+2. `་པའི་སེམས་སྐྱེས་ཆེན་ཨུ་ཡོན་`
+3. `ང་།_མདོ་སྡུད་པ་ཅན་ཟན་རི`
 
 
 ### Key Findings
 
-- **Best Predictability:** Context-2 with 73.5% predictability
+- **Best Predictability:** Context-4 (word) with 89.3% predictability
 - **Branching Factor:** Decreases with context size (more deterministic)
-- **Memory Trade-off:** Larger contexts require more storage (489,183 contexts)
+- **Memory Trade-off:** Larger contexts require more storage (765,950 contexts)
 - **Recommendation:** Context-3 or Context-4 for text generation
 
 ---
@@ -245,64 +314,64 @@ Below are text samples generated from each Markov chain model:
 
 | Metric | Value |
 |--------|-------|
-| Vocabulary Size | 13,016 |
-| Total Tokens | 18,343,262 |
-| Mean Frequency | 1409.29 |
-| Median Frequency | 3 |
-| Frequency Std Dev | 31347.07 |
+| Vocabulary Size | 18,720 |
+| Total Tokens | 7,245,735 |
+| Mean Frequency | 387.06 |
+| Median Frequency | 5 |
+| Frequency Std Dev | 3716.05 |
 
 ### Most Common Words
 
 | Rank | Word | Frequency |
 |------|------|-----------|
-| 1 | ས | 1,859,452 |
-| 2 | ར | 1,242,082 |
-| 3 | ད | 1,225,016 |
-| 4 | ན | 1,119,190 |
-| 5 | ག | 979,844 |
-| 6 | ལ | 962,286 |
-| 7 | བ | 831,513 |
-| 8 | ང | 704,629 |
-| 9 | མ | 647,161 |
-| 10 | པ | 638,483 |
+| 1 | པ | 262,584 |
+| 2 | དང | 156,471 |
+| 3 | ལ | 145,900 |
+| 4 | བ | 121,705 |
+| 5 | པའི | 110,790 |
+| 6 | མ | 88,147 |
+| 7 | དེ | 78,304 |
+| 8 | ནི | 74,845 |
+| 9 | ཀྱི | 70,464 |
+| 10 | དུ | 70,132 |
 
 ### Least Common Words (from vocabulary)
 
 | Rank | Word | Frequency |
 |------|------|-----------|
-| 1 | ༡༡༦༠ | 2 |
-| 2 | w1kg9520 | 2 |
-| 3 | jayasena | 2 |
-| 4 | ༡༡ཙམ | 2 |
-| 5 | 252591 | 2 |
-| 6 | 2525b4 | 2 |
-| 7 | 2525b2 | 2 |
-| 8 | caryā | 2 |
-| 9 | gīti | 2 |
-| 10 | caryāgītivṛtti | 2 |
+| 1 | པིཎྜཱརྠ | 2 |
+| 2 | saṃgraha | 2 |
+| 3 | kṛṣṇācārya | 2 |
+| 4 | པཽཥྚཱི | 2 |
+| 5 | ānanda | 2 |
+| 6 | cakṣu | 2 |
+| 7 | link | 2 |
+| 8 | ལུམྦཱི | 2 |
+| 9 | mine | 2 |
+| 10 | vidhi | 2 |
 
 ### Zipf's Law Analysis
 
 | Metric | Value |
 |--------|-------|
-| Zipf Coefficient | 1.8006 |
-| R² (Goodness of Fit) | 0.975288 |
+| Zipf Coefficient | 2.0020 |
+| R² (Goodness of Fit) | 0.960991 |
 | Adherence Quality | **excellent** |
 
 ### Coverage Analysis
 
 | Top N Words | Coverage |
 |-------------|----------|
-| Top 100 | 92.9% |
-| Top 1,000 | 99.6% |
-| Top 5,000 | 99.9% |
-| Top 10,000 | 100.0% |
+| Top 100 | 47.5% |
+| Top 1,000 | 90.4% |
+| Top 5,000 | 99.1% |
+| Top 10,000 | 99.7% |
 
 ### Key Findings
 
-- **Zipf Compliance:** R²=0.9753 indicates excellent adherence to Zipf's law
-- **High Frequency Dominance:** Top 100 words cover 92.9% of corpus
-- **Long Tail:** 3,016 words needed for remaining 0.0% coverage
+- **Zipf Compliance:** R²=0.9610 indicates excellent adherence to Zipf's law
+- **High Frequency Dominance:** Top 100 words cover 47.5% of corpus
+- **Long Tail:** 8,720 words needed for remaining 0.3% coverage
 
 ---
 ## 5. Word Embeddings Evaluation
@@ -315,24 +384,76 @@ Below are text samples generated from each Markov chain model:
 
 ![t-SNE Sentences](visualizations/tsne_sentences.png)
 
-### Model Comparison
 
-| Model | Vocab Size | Dimension | Avg Norm | Std Norm | Isotropy |
-|-------|------------|-----------|----------|----------|----------|
-| **mono_32d** | 8,661 | 32 | 6.077 | 1.370 | 0.7739 🏆 |
-| **mono_64d** | 8,661 | 64 | 6.426 | 1.018 | 0.7102 |
-| **mono_128d** | 8,661 | 128 | 6.678 | 0.842 | 0.5344 |
-| **embeddings_enhanced** | 0 | 0 | 0.000 | 0.000 | 0.0000 |
+### 5.1 Cross-Lingual Alignment
+
+> *Note: Multilingual alignment visualization not available for this language.*
+
+
+### 5.2 Model Comparison
+
+| Model | Dimension | Isotropy | Semantic Density | Alignment R@1 | Alignment R@10 |
+|-------|-----------|----------|------------------|---------------|----------------|
+| **mono_32d** | 32 | 0.8494 🏆 | 0.3707 | N/A | N/A |
+| **mono_64d** | 64 | 0.7912 | 0.3092 | N/A | N/A |
+| **mono_128d** | 128 | 0.5757 | 0.2954 | N/A | N/A |
 
 ### Key Findings
 
-- **Best Isotropy:** mono_32d with 0.7739 (more uniform distribution)
-- **Dimension Trade-off:** Higher dimensions capture more semantics but reduce isotropy
-- **Vocabulary Coverage:** All models cover 8,661 words
-- **Recommendation:** 100d for balanced semantic capture and efficiency
+- **Best Isotropy:** mono_32d with 0.8494 (more uniform distribution)
+- **Semantic Density:** Average pairwise similarity of 0.3251. Lower values indicate better semantic separation.
+- **Alignment Quality:** No aligned models evaluated in this run.
+- **Recommendation:** 128d aligned for best cross-lingual performance
 
 ---
-## 6. Summary & Recommendations
+## 6.  Morphological Analysis (Experimental)
+
+> ⚠️ **Warning:** This language shows low morphological productivity. The statistical signals used for this analysis may be noisy or less reliable than for morphologically rich languages.
+
+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 | **0.000** | Low morphological productivity | ⚠️ Likely unreliable |
+| Idiomaticity Gap | **-1.000** | 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.
+
+*No productive affixes detected.*
+
+
+### 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.
+
+*No significant bound stems detected.*
+
+
+### 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.
+
+*No significant affix co-occurrences detected.*
+
+
+### 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`).
+
+*Insufficient data for recursive segmentation.*
+
+
+### 6.6 Linguistic Interpretation
+
+> **Automated Insight:**
+The language BO appears to be more isolating or has a highly fixed vocabulary. Word-level models perform nearly as well as subword models, indicating fewer productive morphological processes.
+
+---
+## 7. Summary & Recommendations
 
 ![Performance Dashboard](visualizations/performance_dashboard.png)
 
@@ -340,11 +461,12 @@ Below are text samples generated from each Markov chain model:
 
 | Component | Recommended | Rationale |
 |-----------|-------------|-----------|
-| Tokenizer | **32k BPE** | Best compression (5.96x) with low UNK rate |
-| N-gram | **5-gram** | Lowest perplexity (259) |
-| Markov | **Context-4** | Highest predictability (73.5%) |
+| Tokenizer | **64k BPE** | Best compression (5.30x) |
+| N-gram | **2-gram** | Lowest perplexity (469) |
+| Markov | **Context-4** | Highest predictability (89.3%) |
 | Embeddings | **100d** | Balanced semantic capture and isotropy |
 
+
 ---
 ## Appendix: Metrics Glossary & Interpretation Guide
 
@@ -534,7 +656,8 @@ If you use these models in your research, please cite:
   author = {Kamali, Omar},
   title = {Wikilangs: Open NLP Models for Wikipedia Languages},
   year = {2025},
-  publisher = {HuggingFace},
+  doi = {10.5281/zenodo.18073153},
+  publisher = {Zenodo},
   url = {https://huggingface.co/wikilangs}
   institution = {Omneity Labs}
 }
@@ -550,7 +673,8 @@ MIT License - Free for academic and commercial use.
 - 🤗 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: 2025-12-28 07:45:49*
+*Report Date: 2026-01-03 07:43:59*

models/embeddings/monolingual/bo_128d.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d28fd32d66a933b9d54910c53ae79e731552039f72a158a509f33345be938c
-size 1033296964
+oid sha256:4d7589a8e32a4a14dff0415d4773f3b2c21bcb132b01f0cdcdbb3fd5cac2d0a7
+size 1031854630

models/embeddings/monolingual/bo_128d_metadata.json

@@ -3,11 +3,13 @@
   "dimension": 128,
   "version": "monolingual",
   "training_params": {
-    "dim": 128,
+    "algorithm": "skipgram",
     "min_count": 5,
     "window": 5,
     "negative": 5,
-    "epochs": 5
+    "epochs": 5,
+    "encoding_method": "rope",
+    "dim": 128
   },
-  "vocab_size": 8661
+  "vocab_size": 7310
 }

models/embeddings/monolingual/bo_32d.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f7ec38e53b69d6fe0c7bf028ecf260182dc2c464b0a3998b36285dcdcd0d790
-size 258645316
+oid sha256:25945951b2d9bd762b4aa107b6b33d9788f48752c00df6bb74be80ee7c245721
+size 258240550

models/embeddings/monolingual/bo_32d_metadata.json

@@ -3,11 +3,13 @@
   "dimension": 32,
   "version": "monolingual",
   "training_params": {
-    "dim": 32,
+    "algorithm": "skipgram",
     "min_count": 5,
     "window": 5,
     "negative": 5,
-    "epochs": 5
+    "epochs": 5,
+    "encoding_method": "rope",
+    "dim": 32
   },
-  "vocab_size": 8661
+  "vocab_size": 7310
 }

models/embeddings/monolingual/bo_64d.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a39136f57bc0193b521701d5895d97332f84bef7738e48d579bf3e941611efb
-size 516862532
+oid sha256:05e343618ad45867434c979594e5c58131520908c00fb32eeb884a9598ae5c2d
+size 516111910

models/embeddings/monolingual/bo_64d_metadata.json

@@ -3,11 +3,13 @@
   "dimension": 64,
   "version": "monolingual",
   "training_params": {
-    "dim": 64,
+    "algorithm": "skipgram",
     "min_count": 5,
     "window": 5,
     "negative": 5,
-    "epochs": 5
+    "epochs": 5,
+    "encoding_method": "rope",
+    "dim": 64
   },
-  "vocab_size": 8661
+  "vocab_size": 7310
 }

models/subword_markov/bo_markov_ctx1_subword.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe6b72dd2f3cb1ce71f886ce79e1991ebc9d866ba3d8e9a4e0765a566abef832
-size 295033
+oid sha256:9bca36abfeb85c32777f9e7088e594c535d131c8aea9a20d599c33315361efed
+size 432607

models/subword_markov/bo_markov_ctx1_subword_metadata.json

@@ -2,6 +2,6 @@
   "context_size": 1,
   "variant": "subword",
   "language": "bo",
-  "unique_contexts": 4527,
-  "total_transitions": 51775331
+  "unique_contexts": 8378,
+  "total_transitions": 22713130
 }

models/subword_markov/bo_markov_ctx2_subword.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1343c1704ab694d0457b93b45cf4513b9cc61d7f7b379f22055ad12bdb3453f7
-size 1399204
+oid sha256:f9ea9da39850551788d4eaec8b6dac589a7513f5cd8a9bc6e26566f17ac36287
+size 1811900

models/subword_markov/bo_markov_ctx2_subword_metadata.json

@@ -2,6 +2,6 @@
   "context_size": 2,
   "variant": "subword",
   "language": "bo",
-  "unique_contexts": 45909,
-  "total_transitions": 51761048
+  "unique_contexts": 57113,
+  "total_transitions": 22700930
 }

models/subword_markov/bo_markov_ctx3_subword.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:238ba3561b2e3bbe4353470450e8e2a855ebb948f45a77fec280ddd79e71a6a7
-size 4147532
+oid sha256:592d4d34357c96997930f7a0d9aa2f06a8cef2b6ce1424d18b9c926d509600ea
+size 6648848

models/subword_markov/bo_markov_ctx3_subword_metadata.json

@@ -2,6 +2,6 @@
   "context_size": 3,
   "variant": "subword",
   "language": "bo",
-  "unique_contexts": 168571,
-  "total_transitions": 51746765
+  "unique_contexts": 233848,
+  "total_transitions": 22688730
 }

models/subword_markov/bo_markov_ctx4_subword.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:350c4223d741dac9f5df6b518504739dec14c750eeba2ee92fbe4f3e7793abd0
-size 11386093
+oid sha256:6eb47b6d454ebb16771c614d17731ae5c2763137d58fcb511068e632490768da
+size 18752183

models/subword_markov/bo_markov_ctx4_subword_metadata.json

@@ -2,6 +2,6 @@
   "context_size": 4,
   "variant": "subword",
   "language": "bo",
-  "unique_contexts": 489183,
-  "total_transitions": 51732482
+  "unique_contexts": 765950,
+  "total_transitions": 22676530
 }

models/subword_ngram/bo_2gram_subword.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d63fe48d7e16314165daac5a09388e1993a92697e7057f3ca8766f9e8eccfe1e
-size 139446
+oid sha256:b741663b924d6701ddf3061df84aeb993129494f05dbf2c3f13b1b796a281ca7
+size 216011

models/subword_ngram/bo_2gram_subword_metadata.json

@@ -2,6 +2,6 @@
   "n": 2,
   "variant": "subword",
   "language": "bo",
-  "unique_ngrams": 10716,
-  "total_ngrams": 51775331
+  "unique_ngrams": 14734,
+  "total_ngrams": 22713130
 }

models/subword_ngram/bo_3gram_subword.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db32beee277ce5b96116ccb7fcb3a4f8100711767d8803de99225390f28611b6
-size 784140
+oid sha256:abf34078d1e786d65a97141325854d312713c2230be0def57e7f299e03d9f735
+size 1203727

models/subword_ngram/bo_3gram_subword_metadata.json

@@ -2,6 +2,6 @@
   "n": 3,
   "variant": "subword",
   "language": "bo",
-  "unique_ngrams": 61755,
-  "total_ngrams": 51761048
+  "unique_ngrams": 86351,
+  "total_ngrams": 22700930
 }

models/subword_ngram/bo_4gram_subword.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dfa2e76430d6ce1f681949cc2acbe14cc49ddf452d17256204e4387b0a24cc6
-size 2949767
+oid sha256:d94ccc56cc64b3abed99bb82e501c14f9d76c46160d144d960d1f21e1afd3e74
+size 5706148

models/subword_ngram/bo_4gram_subword_metadata.json

@@ -2,6 +2,6 @@
   "n": 4,
   "variant": "subword",
   "language": "bo",
-  "unique_ngrams": 237121,
-  "total_ngrams": 51746765
+  "unique_ngrams": 391088,
+  "total_ngrams": 22688730
 }

models/tokenizer/bo_tokenizer_16k.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab010daa62bc41c1b8032f9d748af4fd37db53dee73a43da0d904f4823dd00e
-size 703550
+oid sha256:b80644ab76ef9f1236204c625c4e4dacd553df77f82729816a4c8648fac85d0f
+size 682438

models/tokenizer/bo_tokenizer_32k.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40f36be3bd4045efa166c3cb5f777437692dfa9587f1e56e7fbb3e723de6eba9
-size 1237082
+oid sha256:099deda5fa2f785fb901ef55b737350aa4362ed293d20131e1a8d111b9cb3b59
+size 1197306

models/tokenizer/bo_tokenizer_64k.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c954964333d2da25bea610a3945473fa0588b9e1f80593834b369fdb080402a0
-size 2362449
+oid sha256:e1346dc7d382bd75b96573d9f0123d6b2b1fa17c2cdfca58ee3e0289e2c5ab80
+size 2340697

models/tokenizer/bo_tokenizer_8k.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea17dc7300f482ce3d9c095d25a6131c7ed3dd8f32ff3049fea997cc38cbb782
-size 454260
+oid sha256:3c734632bf663d3ae5074f8a9e3e315b68abee224608a9a41d7a6cad565ec452
+size 442308

models/vocabulary/bo_vocabulary.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eeece097f87af2ab0ce9e55f44cb872a6e4f828118a6c10d018670e7b075bbb
-size 213596
+oid sha256:cfa52cc050640e4828a3dd12a129e73d77eccd600656e7e8ecac1d73d7e04695
+size 326513

models/vocabulary/bo_vocabulary_metadata.json

@@ -1,16 +1,17 @@
 {
   "language": "bo",
-  "vocabulary_size": 13016,
+  "vocabulary_size": 18720,
+  "variant": "full",
   "statistics": {
-    "type_token_ratio": 0.0022376683701338307,
+    "type_token_ratio": 0.006158586066529067,
     "coverage": {
-      "top_100": 0.9279372697332342,
-      "top_1000": 0.9940718580638173,
-      "top_5000": 0.9973993752774359,
-      "top_10000": 0.9981424886732634
+      "top_100": 0.4733026861716062,
+      "top_1000": 0.9009478947369145,
+      "top_5000": 0.9874471227821341,
+      "top_10000": 0.9934588401027036
     },
-    "hapax_count": 28093,
-    "hapax_ratio": 0.6833783356442629,
-    "total_documents": 14283
+    "hapax_count": 26064,
+    "hapax_ratio": 0.5819935691318328,
+    "total_documents": 12200
   }
 }

models/word_markov/bo_markov_ctx1_word.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51a4478f179efe4762715a399df064c2175ac4508700aa5231ca3f2241d9baa8
-size 1444473
+oid sha256:28be79310aca5cc300584166fdaf88159c29ab0b3c1a8a528b951d63a306c412
+size 3808759

models/word_markov/bo_markov_ctx1_word_metadata.json

@@ -2,6 +2,6 @@
   "context_size": 1,
   "variant": "word",
   "language": "bo",
-  "unique_contexts": 41503,
-  "total_transitions": 43169277
+  "unique_contexts": 44551,
+  "total_transitions": 7259599
 }

models/word_markov/bo_markov_ctx2_word.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f391dd5db47185870344cb2760e2499b029b58579a143fa623dcb9747232575
-size 3531426
+oid sha256:e4348c33a538330f70aeb91a4ca305d25fef537360b7e48e26baa9e5158477d4
+size 25145984

models/word_markov/bo_markov_ctx2_word_metadata.json

@@ -2,6 +2,6 @@
   "context_size": 2,
   "variant": "word",
   "language": "bo",
-  "unique_contexts": 135576,
-  "total_transitions": 43154994
+  "unique_contexts": 792341,
+  "total_transitions": 7247399
 }

models/word_markov/bo_markov_ctx3_word.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ed95c18ea1ad5d5136b568a6334b628dd4b3b1e75fc8e5b4f09af2322d1f4d2
-size 9151444
+oid sha256:ad9f484c6f87c9af2e6a0b055908c920cdb212dd93e7334c0fb71cd19796ca1d
+size 68659503

models/word_markov/bo_markov_ctx3_word_metadata.json

@@ -2,6 +2,6 @@
   "context_size": 3,
   "variant": "word",
   "language": "bo",
-  "unique_contexts": 373945,
-  "total_transitions": 43140711
+  "unique_contexts": 2987004,
+  "total_transitions": 7235199
 }

models/word_markov/bo_markov_ctx4_word.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7238c4b068f37f9deb6d6f25e25cd27d86fbecff6228c94b188cb8f861f7f7c
-size 22175465
+oid sha256:eab3f700236e7f79ba6cb9a77838c8e911d34df7c8d1732a434003e8c79fa6da
+size 103278579

models/word_markov/bo_markov_ctx4_word_metadata.json

@@ -2,6 +2,6 @@
   "context_size": 4,
   "variant": "word",
   "language": "bo",
-  "unique_contexts": 884085,
-  "total_transitions": 43126429
+  "unique_contexts": 4767837,
+  "total_transitions": 7222999
 }

models/word_ngram/bo_2gram_word.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9b0fcbc93bc920804d2780f7b1ac6cc27c0d8317fc2680aa979f081e0f102a1
-size 240285
+oid sha256:b215d956ef6128f37f2fe173259f0c1760c5ae477fe06b994f2786241aedfd0a
+size 2552232

models/word_ngram/bo_2gram_word_metadata.json

@@ -2,6 +2,6 @@
   "n": 2,
   "variant": "word",
   "language": "bo",
-  "unique_ngrams": 16730,
-  "total_ngrams": 43169277
+  "unique_ngrams": 160381,
+  "total_ngrams": 7259599
 }

models/word_ngram/bo_3gram_word.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e71ca878d82f6d8e0a1f3f01aa1350846d2870fdadfca3da38183eb64306aa9b
-size 1495235
+oid sha256:03fad5b4d1bd8fb2ce2aabbabf517f401438082e42441b024de495262c9ed34a
+size 8849454

models/word_ngram/bo_3gram_word_metadata.json

@@ -2,6 +2,6 @@
   "n": 3,
   "variant": "word",
   "language": "bo",
-  "unique_ngrams": 107789,
-  "total_ngrams": 43154994
+  "unique_ngrams": 482234,
+  "total_ngrams": 7247399
 }

models/word_ngram/bo_4gram_word.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c6d114cdab9167d30db5263ec4923cc3598ee22259e5e41b51e2a9f26d24919
-size 5818114
+oid sha256:cf1b2e7a1bc72005dad39eabec92905b1730dd8e0a888c20d7b57ecb6e67aa90
+size 19665718

models/word_ngram/bo_4gram_word_metadata.json

@@ -2,6 +2,6 @@
   "n": 4,
   "variant": "word",
   "language": "bo",
-  "unique_ngrams": 410390,
-  "total_ngrams": 43140711
+  "unique_ngrams": 997749,
+  "total_ngrams": 7235199
 }