Upload all models and assets for rm (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: rm
+language_name: Romansh
+language_family: romance_galloitalic
+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-romance_galloitalic
+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: 4.365
+  - name: best_isotropy
+    type: isotropy
+    value: 0.8474
+  - name: vocabulary_size
+    type: vocab
+    value: 0
+generated: 2026-01-10
+---
+
+# Romansh - Wikilangs Models
+## Comprehensive Research Report & Full Ablation Study
+
+This repository contains NLP models trained and evaluated by Wikilangs, specifically on **Romansh** 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** | 3.691x | 3.69 | 0.0557% | 645,740 |
+| **16k** | 3.994x | 4.00 | 0.0603% | 596,871 |
+| **32k** | 4.211x | 4.21 | 0.0636% | 566,002 |
+| **64k** | 4.365x 🏆 | 4.37 | 0.0659% | 546,149 |
+
+### Tokenization Examples
+
+Below are sample sentences tokenized with each vocabulary size:
+
+**Sample 1:** `Neyruz-sur-Moudon è ina vischnanca svizra en il chantun Vad en il district Gros-...`
+
+| Vocab | Tokens | Count |
+|-------|--------|-------|
+| 8k | `▁n ey ruz - sur - moudon ▁è ▁ina ▁vischnanca ... (+21 more)` | 31 |
+| 16k | `▁neyruz - sur - moudon ▁è ▁ina ▁vischnanca ▁svizra ▁en ... (+19 more)` | 29 |
+| 32k | `▁neyruz - sur - moudon ▁è ▁ina ▁vischnanca ▁svizra ▁en ... (+19 more)` | 29 |
+| 64k | `▁neyruz - sur - moudon ▁è ▁ina ▁vischnanca ▁svizra ▁en ... (+19 more)` | 29 |
+
+**Sample 2:** `Charmoille e ina fracziun da la vischnanca La Baroche dal chantun Giura en il di...`
+
+| Vocab | Tokens | Count |
+|-------|--------|-------|
+| 8k | `▁char mo ille ▁e ▁ina ▁fracziun ▁da ▁la ▁vischnanca ▁la ... (+16 more)` | 26 |
+| 16k | `▁char mo ille ▁e ▁ina ▁fracziun ▁da ▁la ▁vischnanca ▁la ... (+15 more)` | 25 |
+| 32k | `▁charmoille ▁e ▁ina ▁fracziun ▁da ▁la ▁vischnanca ▁la ▁baroche ▁dal ... (+13 more)` | 23 |
+| 64k | `▁charmoille ▁e ▁ina ▁fracziun ▁da ▁la ▁vischnanca ▁la ▁baroche ▁dal ... (+13 more)` | 23 |
+
+**Sample 3:** `Hérémence è ina citad svizra en il chantun Vallais è ina district Hérens. en il ...`
+
+| Vocab | Tokens | Count |
+|-------|--------|-------|
+| 8k | `▁hér é men ce ▁è ▁ina ▁citad ▁svizra ▁en ▁il ... (+14 more)` | 24 |
+| 16k | `▁hérémence ▁è ▁ina ▁citad ▁svizra ▁en ▁il ▁chantun ▁vallais ▁è ... (+11 more)` | 21 |
+| 32k | `▁hérémence ▁è ▁ina ▁citad ▁svizra ▁en ▁il ▁chantun ▁vallais ▁è ... (+11 more)` | 21 |
+| 64k | `▁hérémence ▁è ▁ina ▁citad ▁svizra ▁en ▁il ▁chantun ▁vallais ▁è ... (+11 more)` | 21 |
+
+
+### Key Findings
+
+- **Best Compression:** 64k achieves 4.365x compression
+- **Lowest UNK Rate:** 8k with 0.0557% 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 | 17,916 | 14.13 | 74,933 | 14.7% | 35.1% |
+| **2-gram** | Subword | 230 🏆 | 7.85 | 3,376 | 70.8% | 99.4% |
+| **3-gram** | Word | 53,185 | 15.70 | 119,039 | 6.2% | 19.2% |
+| **3-gram** | Subword | 1,797 | 10.81 | 27,903 | 30.0% | 75.9% |
+| **4-gram** | Word | 94,120 | 16.52 | 161,618 | 4.4% | 13.1% |
+| **4-gram** | Subword | 9,576 | 13.23 | 144,146 | 14.9% | 43.5% |
+| **5-gram** | Word | 54,308 | 15.73 | 84,789 | 5.6% | 15.5% |
+| **5-gram** | Subword | 34,278 | 15.07 | 382,834 | 8.4% | 26.7% |
+
+### Top 5 N-grams by Size
+
+**2-grams (Word):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `da la` | 32,817 |
+| 2 | `da l` | 19,781 |
+| 3 | `en il` | 16,052 |
+| 4 | `en la` | 9,522 |
+| 5 | `da las` | 8,260 |
+
+**3-grams (Word):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `en il chantun` | 2,817 |
+| 2 | `ultra da quai` | 1,397 |
+| 3 | `svizra en il` | 1,207 |
+| 4 | `è ina vischnanca` | 1,203 |
+| 5 | `en l europa` | 1,148 |
+
+**4-grams (Word):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `svizra en il chantun` | 1,050 |
+| 2 | `en il chantun vad` | 779 |
+| 3 | `è ina vischnanca svizra` | 586 |
+| 4 | `vischnanca svizra en il` | 585 |
+| 5 | `è ina vischnanca politica` | 584 |
+
+**5-grams (Word):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `ina vischnanca svizra en il` | 583 |
+| 2 | `è ina vischnanca svizra en` | 582 |
+| 3 | `vischnanca svizra en il chantun` | 565 |
+| 4 | `è ina vischnanca politica svizra` | 508 |
+| 5 | `vischnanca politica svizra en il` | 484 |
+
+**2-grams (Subword):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `a _` | 758,306 |
+| 2 | `s _` | 412,089 |
+| 3 | `_ d` | 368,200 |
+| 4 | `n _` | 345,394 |
+| 5 | `d a` | 340,317 |
+
+**3-grams (Subword):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `_ d a` | 247,757 |
+| 2 | `d a _` | 210,483 |
+| 3 | `_ l a` | 159,443 |
+| 4 | `l a _` | 151,625 |
+| 5 | `a s _` | 133,920 |
+
+**4-grams (Subword):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `_ d a _` | 165,902 |
+| 2 | `_ l a _` | 117,111 |
+| 3 | `_ i l _` | 76,863 |
+| 4 | `d a _ l` | 68,179 |
+| 5 | `_ e n _` | 64,184 |
+
+**5-grams (Subword):**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `_ d a _ l` | 65,677 |
+| 2 | `a _ l a _` | 48,613 |
+| 3 | `d a _ l a` | 43,880 |
+| 4 | `a _ d a _` | 41,853 |
+| 5 | `_ d a l _` | 40,324 |
+
+
+### Key Findings
+
+- **Best Perplexity:** 2-gram (subword) with 230
+- **Entropy Trend:** Decreases with larger n-grams (more predictable)
+- **Coverage:** Top-1000 patterns cover ~27% 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 | 1.0978 | 2.140 | 8.07 | 124,534 | 0.0% |
+| **1** | Subword | 1.2098 | 2.313 | 10.41 | 715 | 0.0% |
+| **2** | Word | 0.3787 | 1.300 | 2.03 | 1,003,829 | 62.1% |
+| **2** | Subword | 1.0702 | 2.100 | 6.71 | 7,436 | 0.0% |
+| **3** | Word | 0.1550 | 1.113 | 1.30 | 2,037,689 | 84.5% |
+| **3** | Subword | 0.9144 | 1.885 | 4.63 | 49,875 | 8.6% |
+| **4** | Word | 0.0598 🏆 | 1.042 | 1.09 | 2,637,985 | 94.0% |
+| **4** | Subword | 0.7105 | 1.636 | 3.08 | 231,080 | 29.0% |
+
+### Generated Text Samples (Word-based)
+
+Below are text samples generated from each word-based Markov chain model:
+
+**Context Size 1:**
+
+1. `da chasa nova relaziun tranter ils liuns ma a moda optimala dal 18avel tschientaner èn vastas`
+2. `la frantscha da meters pudaiva l osce è pront per l emprova da stgaudament global wealth`
+3. `il palatinat sco terz nivel da la fom vegnivan pretendidas da l enviern utschels aves urden`
+
+**Context Size 2:**
+
+1. `da la pagina center small panorama da hamburg èn ins puspè reavert ina lingia da la musica`
+2. `da l akademie der wissenschaften minca p 270 christine lienemann perrin wolfgang lienemann ed politi...`
+3. `en il vest latin da la federaziun da medis ed ospitals privats il tractament dal retg pippin`
+
+**Context Size 3:**
+
+1. `en il chantun vallais dal chantun vallais en il chantun tessin vischnancas svizras maggia`
+2. `ultra da quai il concept da la strategia u da la tora la quala furma l emprim epos`
+3. `svizra en il chantun friburg en il district jura nord vaudois en il chantun vad en il district`
+
+**Context Size 4:**
+
+1. `svizra en il chantun vad en il district nyon en il chantun vad dal chantun vad`
+2. `en il chantun vad dal chantun vad`
+3. `è ina vischnanca svizra en il chantun tessin che appartegna al circul verzasca dal district locarno ...`
+
+
+### Generated Text Samples (Subword-based)
+
+Below are text samples generated from each subword-based Markov chain model:
+
+**Context Size 1:**
+
+1. `_c_castaun:_s_ch`
+2. `a_iolasil_ialèn_`
+3. `ig_ilema_sgn_rim`
+
+**Context Size 2:**
+
+1. `a_che_betg_un_las`
+2. `s_p._ofarling_prü`
+3. `_da_l’il_co_er,_d`
+
+**Context Size 3:**
+
+1. `_da_nadella_gronis`
+2. `da_la_dal_probalk:`
+3. `_la_da_diffenser_l`
+
+**Context Size 4:**
+
+1. `_da_s._p._38s._part`
+2. `_la_mauren_ha_il_cu`
+3. `_il_territoric_è_la`
+
+
+### Key Findings
+
+- **Best Predictability:** Context-4 (word) with 94.0% predictability
+- **Branching Factor:** Decreases with context size (more deterministic)
+- **Memory Trade-off:** Larger contexts require more storage (231,080 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 | 63,266 |
+| Total Tokens | 3,028,553 |
+| Mean Frequency | 47.87 |
+| Median Frequency | 4 |
+| Frequency Std Dev | 1094.76 |
+
+### Most Common Words
+
+| Rank | Word | Frequency |
+|------|------|-----------|
+| 1 | da | 166,290 |
+| 2 | la | 118,196 |
+| 3 | il | 79,956 |
+| 4 | l | 69,320 |
+| 5 | en | 67,320 |
+| 6 | e | 53,149 |
+| 7 | dal | 40,449 |
+| 8 | a | 39,768 |
+| 9 | è | 33,261 |
+| 10 | ils | 31,735 |
+
+### Least Common Words (from vocabulary)
+
+| Rank | Word | Frequency |
+|------|------|-----------|
+| 1 | planisadra | 2 |
+| 2 | hzr | 2 |
+| 3 | khizr | 2 |
+| 4 | pereslawl | 2 |
+| 5 | zalesskij | 2 |
+| 6 | tawjihi | 2 |
+| 7 | gate | 2 |
+| 8 | palestinians | 2 |
+| 9 | tregua | 2 |
+| 10 | cumpusiziun | 2 |
+
+### Zipf's Law Analysis
+
+| Metric | Value |
+|--------|-------|
+| Zipf Coefficient | 1.0749 |
+| R² (Goodness of Fit) | 0.994918 |
+| Adherence Quality | **excellent** |
+
+### Coverage Analysis
+
+| Top N Words | Coverage |
+|-------------|----------|
+| Top 100 | 45.9% |
+| Top 1,000 | 68.3% |
+| Top 5,000 | 84.5% |
+| Top 10,000 | 90.3% |
+
+### Key Findings
+
+- **Zipf Compliance:** R²=0.9949 indicates excellent adherence to Zipf's law
+- **High Frequency Dominance:** Top 100 words cover 45.9% of corpus
+- **Long Tail:** 53,266 words needed for remaining 9.7% 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 | 0.8474 | 0.3419 | N/A | N/A |
+| **mono_64d** | 64 | 0.8324 | 0.2577 | N/A | N/A |
+| **mono_128d** | 128 | 0.8002 | 0.1915 | N/A | N/A |
+| **aligned_32d** | 32 | 0.8474 🏆 | 0.3398 | 0.1380 | 0.4520 |
+| **aligned_64d** | 64 | 0.8324 | 0.2625 | 0.2280 | 0.5880 |
+| **aligned_128d** | 128 | 0.8002 | 0.1883 | 0.2940 | 0.6020 |
+
+### Key Findings
+
+- **Best Isotropy:** aligned_32d with 0.8474 (more uniform distribution)
+- **Semantic Density:** Average pairwise similarity of 0.2636. Lower values indicate better semantic separation.
+- **Alignment Quality:** Aligned models achieve up to 29.4% 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 | **-0.421** | 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 |
+|--------|----------|
+| `-s` | sylvain, socialdemocratica, strobl |
+| `-a` | ams, aristocrazia, average |
+| `-p` | promoturs, passione, pandemias |
+| `-b` | breton, bloccadas, brünisried |
+| `-c` | communal, champester, consecrar |
+| `-m` | magistrat, moëns, metallurgia |
+| `-d` | demokratisches, dero, deditgà |
+| `-g` | gruscha, gründliche, grammaticalas |
+
+#### Productive Suffixes
+| Suffix | Examples |
+|--------|----------|
+| `-s` | ams, moëns, helveticarchives |
+| `-a` | socialdemocratica, aristocrazia, metallurgia |
+| `-n` | sylvain, breton, tessin |
+| `-as` | explitgadas, aviartas, organellas |
+| `-r` | champester, consecrar, terrur |
+| `-e` | älteste, average, homme |
+| `-t` | magistrat, rendaquint, industriegesellschaft |
+| `-er` | champester, schindler, hausberger |
+
+### 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 |
+|------|----------|------------------|----------|
+| `itad` | 2.01x | 54 contexts | mitad, citad, citads |
+| `ment` | 1.73x | 88 contexts | mument, dement, mentis |
+| `usch` | 1.62x | 86 contexts | kusch, uschè, cusch |
+| `tica` | 1.71x | 62 contexts | etica, antica, betica |
+| `aziu` | 1.71x | 53 contexts | naziun, raziun, grazius |
+| `urma` | 1.84x | 37 contexts | furma, burma, surmar |
+| `ntan` | 1.71x | 42 contexts | entant, sentan, muntan |
+| `egni` | 1.68x | 42 contexts | regni, vegni, tegnia |
+| `iuns` | 2.11x | 18 contexts | liuns, aviuns, uniuns |
+| `ents` | 1.74x | 33 contexts | dents, vents, cents |
+| `furm` | 1.57x | 47 contexts | furma, furmo, furmà |
+| `nter` | 1.40x | 65 contexts | unter, enter, inter |
+
+### 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 |
+|--------|--------|-----------|----------|
+| `-c` | `-s` | 216 words | civitates, carstgauns |
+| `-s` | `-s` | 202 words | sillogissems, soluziuns |
+| `-p` | `-s` | 163 words | polineices, playmates |
+| `-s` | `-a` | 161 words | spendra, spezialisada |
+| `-c` | `-a` | 148 words | cortina, charenta |
+| `-p` | `-a` | 138 words | primministra, preferescha |
+| `-a` | `-s` | 131 words | atletas, abstractas |
+| `-s` | `-n` | 111 words | seen, selen |
+| `-m` | `-s` | 107 words | mémoires, misteris |
+| `-d` | `-s` | 97 words | diabetes, digerids |
+
+### 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 |
+|------|-----------------|------------|------|
+| modernism | **`moderni-s-m`** | 7.5 | `s` |
+| promontori | **`promonto-r-i`** | 7.5 | `r` |
+| democratisà | **`democrati-s-à`** | 7.5 | `s` |
+| chamutsch | **`chamut-s-ch`** | 7.5 | `s` |
+| mediatisà | **`mediati-s-à`** | 7.5 | `s` |
+| hollandse | **`holland-s-e`** | 7.5 | `s` |
+| novreligiusas | **`novreligiu-s-as`** | 7.5 | `s` |
+| cinquesensi | **`cinquesen-s-i`** | 7.5 | `s` |
+| victoriusas | **`victoriu-s-as`** | 7.5 | `s` |
+| pretensiusas | **`pretensiu-s-as`** | 7.5 | `s` |
+| extravagant | **`extravag-a-nt`** | 7.5 | `a` |
+| naziunelas | **`naziun-el-as`** | 6.0 | `naziun` |
+| mesiradas | **`mesira-da-s`** | 6.0 | `mesira` |
+| daventond | **`davent-on-d`** | 6.0 | `davent` |
+| traversavan | **`traversa-va-n`** | 6.0 | `traversa` |
+
+### 6.6 Linguistic Interpretation
+
+> **Automated Insight:**
+The language Romansh 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 (4.36x) |
+| N-gram | **2-gram** | Lowest perplexity (230) |
+| Markov | **Context-4** | Highest predictability (94.0%) |
+| 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: 2026-01-10 18:48:27*

models/embeddings/aligned/rm_128d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fee3eedf3cff898831b6fe1b66d1e1d44eecef214e31f508b295dfed0a82ad8
+size 1064151886

models/embeddings/aligned/rm_128d.meta.json

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

models/embeddings/aligned/rm_128d.projection.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f03e307ff2d87183f25637e2c9df56387ba1470d8d2546974a78b31f77b4509
+size 65664

models/embeddings/aligned/rm_128d_metadata.json

@@ -0,0 +1,8 @@
+{
+  "language": "rm",
+  "dimension": 128,
+  "version": "aligned",
+  "hub_language": "en",
+  "seed_vocab_size": 12635,
+  "vocab_size": 38537
+}

models/embeddings/aligned/rm_32d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900413f2dfa99428ce09a41670bdd614895a5de5c847f91b157e5207001a56c9
+size 266555470

models/embeddings/aligned/rm_32d.meta.json

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

models/embeddings/aligned/rm_32d.projection.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462369d2ae56cd5e40bead1ee1a7f306535cb4197eef57a91fa45f53ba313627
+size 4224

models/embeddings/aligned/rm_32d_metadata.json

@@ -0,0 +1,8 @@
+{
+  "language": "rm",
+  "dimension": 32,
+  "version": "aligned",
+  "hub_language": "en",
+  "seed_vocab_size": 12635,
+  "vocab_size": 38537
+}

models/embeddings/aligned/rm_64d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dbcba65ce29d5f9f8634b42ee9da2497db36d5f420a1d9300c856dec1ed85ca
+size 532420942

models/embeddings/aligned/rm_64d.meta.json

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

models/embeddings/aligned/rm_64d.projection.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9bd1df5df64dd3424bbeea8a678fef4da66498830cd700854a28d32712b0a3a
+size 16512

models/embeddings/aligned/rm_64d_metadata.json

@@ -0,0 +1,8 @@
+{
+  "language": "rm",
+  "dimension": 64,
+  "version": "aligned",
+  "hub_language": "en",
+  "seed_vocab_size": 12635,
+  "vocab_size": 38537
+}

models/embeddings/monolingual/rm_128d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fee3eedf3cff898831b6fe1b66d1e1d44eecef214e31f508b295dfed0a82ad8
+size 1064151886

models/embeddings/monolingual/rm_128d.meta.json

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

models/embeddings/monolingual/rm_128d_metadata.json

@@ -0,0 +1,16 @@
+{
+  "language": "rm",
+  "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": 38537
+}

models/embeddings/monolingual/rm_32d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900413f2dfa99428ce09a41670bdd614895a5de5c847f91b157e5207001a56c9
+size 266555470

models/embeddings/monolingual/rm_32d.meta.json

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

models/embeddings/monolingual/rm_32d_metadata.json

@@ -0,0 +1,16 @@
+{
+  "language": "rm",
+  "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": 38537
+}

models/embeddings/monolingual/rm_64d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dbcba65ce29d5f9f8634b42ee9da2497db36d5f420a1d9300c856dec1ed85ca
+size 532420942

models/embeddings/monolingual/rm_64d.meta.json

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

models/embeddings/monolingual/rm_64d_metadata.json

@@ -0,0 +1,16 @@
+{
+  "language": "rm",
+  "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": 38537
+}

models/subword_markov/rm_markov_ctx1_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5255f3c5c50b3e47ff4f4127ad832bdcd7b1adaa1ff2b1c498b6ec9483eb6769
+size 61220

models/subword_markov/rm_markov_ctx1_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 1,
+  "variant": "subword",
+  "language": "rm",
+  "unique_contexts": 715,
+  "total_transitions": 18350465
+}

models/subword_markov/rm_markov_ctx2_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744f1d843636934233d6ddb631d17ace5693b62a4f003d6a6df739fbadb11601
+size 417117

models/subword_markov/rm_markov_ctx2_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 2,
+  "variant": "subword",
+  "language": "rm",
+  "unique_contexts": 7436,
+  "total_transitions": 18346603
+}

models/subword_markov/rm_markov_ctx3_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daf66b486b54d595c90a3c2b23336867334ec51f139c69bf74a7cfb594133624
+size 1767152

models/subword_markov/rm_markov_ctx3_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 3,
+  "variant": "subword",
+  "language": "rm",
+  "unique_contexts": 49875,
+  "total_transitions": 18342741
+}

models/subword_markov/rm_markov_ctx4_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:753051cfe6ce307a683054017d3bf1eb53674bcdbd1fd6632a641b9dd911fe8f
+size 5371797

models/subword_markov/rm_markov_ctx4_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 4,
+  "variant": "subword",
+  "language": "rm",
+  "unique_contexts": 231080,
+  "total_transitions": 18338879
+}

models/subword_ngram/rm_2gram_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afaaf24ccfb027fd41d154fbb96ab05834ccb35347ab587570e71ddba1450265
+size 46127

models/subword_ngram/rm_2gram_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 2,
+  "variant": "subword",
+  "language": "rm",
+  "unique_ngrams": 3376,
+  "total_ngrams": 18350465
+}

models/subword_ngram/rm_3gram_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9df04a0619a77c640750a521e8cfc3baa6e266831493851ca604bd6472e5ca4b
+size 346415

models/subword_ngram/rm_3gram_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 3,
+  "variant": "subword",
+  "language": "rm",
+  "unique_ngrams": 27903,
+  "total_ngrams": 18346603
+}

models/subword_ngram/rm_4gram_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c027bda52c5fb3bf5b85427d343580f00a25d09313a187bc9620cc406a35da9
+size 1633376

models/subword_ngram/rm_4gram_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 4,
+  "variant": "subword",
+  "language": "rm",
+  "unique_ngrams": 144146,
+  "total_ngrams": 18342741
+}

models/subword_ngram/rm_5gram_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c698db7dfb3e5103744ca91cfb8c341c9097236dd31b42ace52175634db8469d
+size 4401866

models/subword_ngram/rm_5gram_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 5,
+  "variant": "subword",
+  "language": "rm",
+  "unique_ngrams": 382834,
+  "total_ngrams": 18338879
+}

models/tokenizer/rm_tokenizer_16k.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d40d9988d9143fcfe0b7f8c4db0929fda34d31c271ff731bafa0ba275c487b00
+size 510258

models/tokenizer/rm_tokenizer_32k.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8956ca9db2be700216e0d6034f59db439304c570e7529949c68d42915cf4f17c
+size 792581

models/tokenizer/rm_tokenizer_64k.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e3cdcebbf691f285a129477890617c4f289d9d63934b12547718bba60d03b61
+size 1376311

models/tokenizer/rm_tokenizer_8k.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d99a9bbc99fcc6e0b380eb72e89d69c95e6a1a586135f4562e6d175f9b107f0d
+size 373234

models/vocabulary/rm_vocabulary.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b52caf1e4194fc4483288b276bcb3ed7541595908b7fa9ee51e402bdae7e710
+size 1115930

models/vocabulary/rm_vocabulary_metadata.json

@@ -0,0 +1,17 @@
+{
+  "language": "rm",
+  "vocabulary_size": 63266,
+  "variant": "full",
+  "statistics": {
+    "type_token_ratio": 0.04031422864266638,
+    "coverage": {
+      "top_100": 0.4496535756405161,
+      "top_1000": 0.6696909754900882,
+      "top_5000": 0.8283011613501229,
+      "top_10000": 0.884821344193832
+    },
+    "hapax_count": 61299,
+    "hapax_ratio": 0.4921045237426243,
+    "total_documents": 3862
+  }
+}

models/word_markov/rm_markov_ctx1_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2207bc9b2c4f8ce11593d3e362608a188803daf9079b915167c5e5023f8e26d
+size 7584394