Upload all models and assets for cdo (20251201)

.gitattributes

@@ -33,3 +33,9 @@ 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/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 +1,553 @@
+---
+language: cdo
+language_name: CDO
+language_family: sinitic_other
+tags:
+  - wikilangs
+  - nlp
+  - tokenizer
+  - embeddings
+  - n-gram
+  - markov
+  - wikipedia
+  - monolingual
+  - family-sinitic_other
+license: mit
+library_name: wikilangs
+pipeline_tag: feature-extraction
+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: 2.796
+  - name: best_isotropy
+    type: isotropy
+    value: 0.5460
+  - name: vocabulary_size
+    type: vocab
+    value: 12714
+generated: 2025-12-28
+---
+
+# CDO - Wikilangs Models
+## Comprehensive Research Report & Full Ablation Study
+
+This repository contains NLP models trained and evaluated by Wikilangs, specifically on **CDO** 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-gram)
+- Markov chains (context of 1, 2, 3 and 4)
+- Subword N-gram and Markov chains
+- Embeddings in various sizes and dimensions
+- 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. Summary & Recommendations](#6-summary--recommendations)
+- [Metrics Glossary](#appendix-metrics-glossary--interpretation-guide)
+- [Visualizations Index](#visualizations-index)
+
+---
+## 1. Tokenizer Evaluation
+
+![Tokenizer Compression](visualizations/tokenizer_compression.png)
+
+### Results
+
+| Vocab Size | Compression | Avg Token Len | UNK Rate | Total Tokens |
+|------------|-------------|---------------|----------|--------------|
+| **32k** | 2.562x | 2.54 | 0.0007% | 298,320 |
+| **64k** | 2.796x 🏆 | 2.77 | 0.0007% | 273,367 |
+
+### Tokenization Examples
+
+Below are sample sentences tokenized with each vocabulary size:
+
+**Sample 1:** `Pender Gông (Ĭng-ngṳ̄: Pender County) sê Mī-guók North Carolina gì siŏh ciáh gôn...`
+
+| Vocab | Tokens | Count |
+|-------|--------|-------|
+| 32k | `▁pen der ▁gông ▁( ĭng - ngṳ̄ : ▁pen der ... (+19 more)` | 29 |
+| 64k | `▁pender ▁gông ▁( ĭng - ngṳ̄ : ▁pender ▁county ) ... (+17 more)` | 27 |
+
+**Sample 2:** `Duâi dâi
+
+Chók-sié
+
+Guó-sié
+
+
+分類:1170 nièng-dâi`
+
+| Vocab | Tokens | Count |
+|-------|--------|-------|
+| 32k | `▁duâi ▁dâi ▁chók - sié ▁guó - sié ▁分類 : ... (+7 more)` | 17 |
+| 64k | `▁duâi ▁dâi ▁chók - sié ▁guó - sié ▁分類 : ... (+7 more)` | 17 |
+
+**Sample 3:** `1000 nièng-dâi téng 1000 nièng 1 nguŏk 1 hô̤ kăi-sṳ̄, gáu 1009 nièng 12 nguŏk 31...`
+
+| Vocab | Tokens | Count |
+|-------|--------|-------|
+| 32k | `▁ 1 0 0 0 ▁nièng - dâi ▁téng ▁ ... (+36 more)` | 46 |
+| 64k | `▁ 1 0 0 0 ▁nièng - dâi ▁téng ▁ ... (+36 more)` | 46 |
+
+
+### Key Findings
+
+- **Best Compression:** 64k achieves 2.796x compression
+- **Lowest UNK Rate:** 32k with 0.0007% 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 Coverage](visualizations/ngram_coverage.png)
+
+### Results
+
+| N-gram | Perplexity | Entropy | Unique N-grams | Top-100 Coverage | Top-1000 Coverage |
+|--------|------------|---------|----------------|------------------|-------------------|
+| **2-gram** | 2,092 🏆 | 11.03 | 13,738 | 34.2% | 70.6% |
+| **2-gram** | 517 🏆 | 9.01 | 13,773 | 57.4% | 92.0% |
+| **3-gram** | 6,902 | 12.75 | 35,914 | 23.0% | 49.3% |
+| **3-gram** | 2,154 | 11.07 | 33,837 | 33.3% | 72.5% |
+| **4-gram** | 16,500 | 14.01 | 75,913 | 16.0% | 37.8% |
+| **4-gram** | 6,830 | 12.74 | 94,271 | 22.4% | 53.8% |
+
+### Top 5 N-grams by Size
+
+**2-grams:**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `分類 :` | 17,792 |
+| 2 | `̤ ng` | 9,653 |
+| 3 | `. 分類` | 8,000 |
+| 4 | `- guók` | 7,750 |
+| 5 | `- sié` | 7,747 |
+
+**3-grams:**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `. 分類 :` | 8,000 |
+| 2 | `gì siŏh ciáh` | 5,565 |
+| 3 | `- ngṳ ̄` | 4,336 |
+| 4 | `mī - guók` | 3,641 |
+| 5 | `gâe ̤ ng` | 3,480 |
+
+**4-grams:**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `sê mī - guók` | 3,211 |
+| 2 | `gì siŏh ciáh gông` | 3,000 |
+| 3 | `ciáh gông . 分類` | 3,000 |
+| 4 | `gông . 分類 :` | 3,000 |
+| 5 | `siŏh ciáh gông .` | 3,000 |
+
+
+### Key Findings
+
+- **Best Perplexity:** 2-gram with 517
+- **Entropy Trend:** Decreases with larger n-grams (more predictable)
+- **Coverage:** Top-1000 patterns cover ~54% of corpus
+- **Recommendation:** 4-gram or 5-gram for best predictive performance
+
+---
+## 3. Markov Chain Evaluation
+
+![Markov Entropy](visualizations/markov_entropy.png)
+
+![Markov Branching](visualizations/markov_branching.png)
+
+### Results
+
+| Context | Avg Entropy | Perplexity | Branching Factor | Unique Contexts | Predictability |
+|---------|-------------|------------|------------------|-----------------|----------------|
+| **1** | 0.2803 | 1.214 | 3.49 | 48,699 | 72.0% |
+| **1** | 0.3942 | 1.314 | 4.02 | 31,614 | 60.6% |
+| **2** | 0.1991 | 1.148 | 1.83 | 169,503 | 80.1% |
+| **2** | 0.3616 | 1.285 | 2.00 | 127,156 | 63.8% |
+| **3** | 0.1556 | 1.114 | 1.42 | 308,939 | 84.4% |
+| **3** | 0.2179 | 1.163 | 1.54 | 253,902 | 78.2% |
+| **4** | 0.0983 🏆 | 1.071 | 1.21 | 437,205 | 90.2% |
+| **4** | 0.1764 🏆 | 1.130 | 1.38 | 389,634 | 82.4% |
+
+### Generated Text Samples
+
+Below are text samples generated from each Markov chain model:
+
+**Context Size 1:**
+
+1. `- hū siék gì siŏh ciáh gông . 分類 : chĭng - uăng - pū -`
+2. `̤ k nâ sáng ĕu - ngiòng ( 螺洲路 ) guōng - dŏng - dōi -`
+3. `gì dâ ̤ 18 艭 ngiê - guók - guó - dók “ . chók -`
+
+**Context Size 2:**
+
+1. `分類 : 1370 nièng - dâi gì lùng - dŭng - ngŏk liù - giù - dôi`
+2. `̤ ng hók - gióng , dâi - biēu gê ̤ ṳng - sāng - dōng gâe`
+3. `. 分類 : 200 nièng - dâi - mā 分類 : 1300年代`
+
+**Context Size 3:**
+
+1. `. 分類 : minnesota gì gông`
+2. `gì siŏh ciáh dê - ngék - chê . 分類 : hù - báe ̤ k - chiă`
+3. `- ngṳ ̄ : lafayette county ) sê mī - guók gì buô - hông gì sṳ ̆`
+
+**Context Size 4:**
+
+1. `sê mī - guók colorado gì siŏh ciáh gông . 分類 : florida gì gông`
+2. `gông . 分類 : michigan gì gông`
+3. `siŏh ciáh gông . 分類 : indiana gì gông`
+
+
+### Key Findings
+
+- **Best Predictability:** Context-4 with 90.2% predictability
+- **Branching Factor:** Decreases with context size (more deterministic)
+- **Memory Trade-off:** Larger contexts require more storage (389,634 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 | 12,714 |
+| Total Tokens | 590,881 |
+| Mean Frequency | 46.47 |
+| Median Frequency | 3 |
+| Frequency Std Dev | 447.20 |
+
+### Most Common Words
+
+| Rank | Word | Frequency |
+|------|------|-----------|
+| 1 | gì | 24,268 |
+| 2 | 分類 | 17,794 |
+| 3 | ng | 16,472 |
+| 4 | sê | 15,967 |
+| 5 | siŏh | 9,713 |
+| 6 | guók | 9,302 |
+| 7 | gông | 9,087 |
+| 8 | sié | 8,595 |
+| 9 | nièng | 7,825 |
+| 10 | dâi | 7,699 |
+
+### Least Common Words (from vocabulary)
+
+| Rank | Word | Frequency |
+|------|------|-----------|
+| 1 | 燈泡厰 | 2 |
+| 2 | 搪瓷厰 | 2 |
+| 3 | 保溫瓶厰 | 2 |
+| 4 | 啤酒厰 | 2 |
+| 5 | 福大機械厰 | 2 |
+| 6 | 抗生素厰 | 2 |
+| 7 | kbo | 2 |
+| 8 | 우주항공청 | 2 |
+| 9 | cho | 2 |
+| 10 | chit | 2 |
+
+### Zipf's Law Analysis
+
+| Metric | Value |
+|--------|-------|
+| Zipf Coefficient | 1.3995 |
+| R² (Goodness of Fit) | 0.979429 |
+| Adherence Quality | **excellent** |
+
+### Coverage Analysis
+
+| Top N Words | Coverage |
+|-------------|----------|
+| Top 100 | 55.6% |
+| Top 1,000 | 90.8% |
+| Top 5,000 | 97.1% |
+| Top 10,000 | 99.1% |
+
+### Key Findings
+
+- **Zipf Compliance:** R²=0.9794 indicates excellent adherence to Zipf's law
+- **High Frequency Dominance:** Top 100 words cover 55.6% of corpus
+- **Long Tail:** 2,714 words needed for remaining 0.9% coverage
+
+---
+## 5. Word Embeddings Evaluation
+
+![Embedding Isotropy](visualizations/embedding_isotropy.png)
+
+![Similarity Matrix](visualizations/embedding_similarity.png)
+
+![t-SNE Words](visualizations/tsne_words.png)
+
+![t-SNE Sentences](visualizations/tsne_sentences.png)
+
+### Model Comparison
+
+| Model | Vocab Size | Dimension | Avg Norm | Std Norm | Isotropy |
+|-------|------------|-----------|----------|----------|----------|
+| **mono_32d** | 7,009 | 32 | 4.149 | 1.118 | 0.5460 🏆 |
+| **mono_64d** | 7,009 | 64 | 4.243 | 1.106 | 0.2037 |
+| **mono_128d** | 7,009 | 128 | 4.233 | 1.119 | 0.0381 |
+| **embeddings_enhanced** | 0 | 0 | 0.000 | 0.000 | 0.0000 |
+
+### Key Findings
+
+- **Best Isotropy:** mono_32d with 0.5460 (more uniform distribution)
+- **Dimension Trade-off:** Higher dimensions capture more semantics but reduce isotropy
+- **Vocabulary Coverage:** All models cover 7,009 words
+- **Recommendation:** 100d for balanced semantic capture and efficiency
+
+---
+## 6. Summary & Recommendations
+
+![Performance Dashboard](visualizations/performance_dashboard.png)
+
+### Production Recommendations
+
+| Component | Recommended | Rationale |
+|-----------|-------------|-----------|
+| Tokenizer | **32k BPE** | Best compression (2.80x) with low UNK rate |
+| N-gram | **5-gram** | Lowest perplexity (517) |
+| Markov | **Context-4** | Highest predictability (90.2%) |
+| 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},
+  publisher = {HuggingFace},
+  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)
+---
+*Generated by Wikilangs Models Pipeline*
+
+*Report Date: 2025-12-28 16:25:16*

models/embeddings/monolingual/cdo_128d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87273b834175c8ffca7ff96a3a21f5890c33eb81fd8bd600e3f7749a3c1efde6
+size 1031314655

models/embeddings/monolingual/cdo_128d.meta.json

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

models/embeddings/monolingual/cdo_128d_metadata.json

@@ -0,0 +1,13 @@
+{
+  "language": "cdo",
+  "dimension": 128,
+  "version": "monolingual",
+  "training_params": {
+    "dim": 128,
+    "min_count": 5,
+    "window": 5,
+    "negative": 5,
+    "epochs": 5
+  },
+  "vocab_size": 7009
+}

models/embeddings/monolingual/cdo_32d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d65b7a0893696382e676534c0654d0fa33b57a4337091da15492cd7c0abf3b48
+size 257931743

models/embeddings/monolingual/cdo_32d.meta.json

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

models/embeddings/monolingual/cdo_32d_metadata.json

@@ -0,0 +1,13 @@
+{
+  "language": "cdo",
+  "dimension": 32,
+  "version": "monolingual",
+  "training_params": {
+    "dim": 32,
+    "min_count": 5,
+    "window": 5,
+    "negative": 5,
+    "epochs": 5
+  },
+  "vocab_size": 7009
+}

models/embeddings/monolingual/cdo_64d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70424ab1f058bf1eec92ffa8c17229b3451d02319f7295d7a82908645320bdb6
+size 515726047

models/embeddings/monolingual/cdo_64d.meta.json

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

models/embeddings/monolingual/cdo_64d_metadata.json

@@ -0,0 +1,13 @@
+{
+  "language": "cdo",
+  "dimension": 64,
+  "version": "monolingual",
+  "training_params": {
+    "dim": 64,
+    "min_count": 5,
+    "window": 5,
+    "negative": 5,
+    "epochs": 5
+  },
+  "vocab_size": 7009
+}

models/subword_markov/cdo_markov_ctx1_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f235b61b31e910d9f0a63bff6431ca1b061d7d60c93f009c3efb2d4dd4d8d94
+size 859391

models/subword_markov/cdo_markov_ctx1_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 1,
+  "variant": "subword",
+  "language": "cdo",
+  "unique_contexts": 31614,
+  "total_transitions": 2905389
+}

models/subword_markov/cdo_markov_ctx2_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95c5781711001d90b8d98035bad77dc2eafa9ca4d93f92cbe4e187b3ca6f467c
+size 2273669

models/subword_markov/cdo_markov_ctx2_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 2,
+  "variant": "subword",
+  "language": "cdo",
+  "unique_contexts": 127156,
+  "total_transitions": 2888681
+}

models/subword_markov/cdo_markov_ctx3_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0112fc9e03100831bb45b13b125d60693af2b6111630b553ae0b8802b325840d
+size 4278912

models/subword_markov/cdo_markov_ctx3_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 3,
+  "variant": "subword",
+  "language": "cdo",
+  "unique_contexts": 253902,
+  "total_transitions": 2871973
+}

models/subword_markov/cdo_markov_ctx4_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:863a8d123baa32acad56367516fba40e4df9fe4d98e2a22ce9e27a3dcadf37ff
+size 6583946

models/subword_markov/cdo_markov_ctx4_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 4,
+  "variant": "subword",
+  "language": "cdo",
+  "unique_contexts": 389634,
+  "total_transitions": 2855265
+}

models/subword_ngram/cdo_2gram_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:429757e59b20addd0ca423c66011cf245936cb430796406a7e56ac432fbc78ff
+size 180569

models/subword_ngram/cdo_2gram_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 2,
+  "variant": "subword",
+  "language": "cdo",
+  "unique_ngrams": 13773,
+  "total_ngrams": 2905389
+}

models/subword_ngram/cdo_3gram_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb21e2e89d34f0d79e0ad314920dfc3371d0dbdc72b20e5448b52c64d94e3daf
+size 481494

models/subword_ngram/cdo_3gram_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 3,
+  "variant": "subword",
+  "language": "cdo",
+  "unique_ngrams": 33837,
+  "total_ngrams": 2888681
+}

models/subword_ngram/cdo_4gram_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f82d92e0227f12077424a14d88f6d50fbac2bc1d12b803abe7c34c6bc8a1e7e
+size 1234369

models/subword_ngram/cdo_4gram_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 4,
+  "variant": "subword",
+  "language": "cdo",
+  "unique_ngrams": 94271,
+  "total_ngrams": 2871973
+}

models/tokenizer/cdo_tokenizer_32k.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29cc26ce42341f87bf600b104422987383bb16aab206d714d8025b627a81318a
+size 652498

models/tokenizer/cdo_tokenizer_64k.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd9f7c3b27cd6d59d2600b4da0253681a1c8987f94a736a1458e336f86ae632c
+size 1220234

models/vocabulary/cdo_vocabulary.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f67094c35332c0e243a9e0fa3b227560d5e7cbeb597f1f5f91eeaae915d87402
+size 220074

models/vocabulary/cdo_vocabulary_metadata.json

@@ -0,0 +1,16 @@
+{
+  "language": "cdo",
+  "vocabulary_size": 12714,
+  "statistics": {
+    "type_token_ratio": 0.07780709085921002,
+    "coverage": {
+      "top_100": 0.5244804991801553,
+      "top_1000": 0.8557711325341176,
+      "top_5000": 0.9148462073409597,
+      "top_10000": 0.9338142876283201
+    },
+    "hapax_count": 36067,
+    "hapax_ratio": 0.7393657366597651,
+    "total_documents": 16708
+  }
+}

models/word_markov/cdo_markov_ctx1_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216d791b7daa8b64656b1cba78bbbc02aa7f5ae7d9bf1ce3a3acf8fc6ca30ad8
+size 2218064

models/word_markov/cdo_markov_ctx1_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 1,
+  "variant": "word",
+  "language": "cdo",
+  "unique_contexts": 48699,
+  "total_transitions": 989207
+}

models/word_markov/cdo_markov_ctx2_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59c0afaec27cafdf472078114f0c1e6330cbc442a0cf86a0de739eb654009647
+size 4081907

models/word_markov/cdo_markov_ctx2_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 2,
+  "variant": "word",
+  "language": "cdo",
+  "unique_contexts": 169503,
+  "total_transitions": 972499
+}

models/word_markov/cdo_markov_ctx3_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a9fad10b27aa485ee443b1b3fb11cf1c68941f562e62e4a5d392900045e177d
+size 6371893

models/word_markov/cdo_markov_ctx3_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 3,
+  "variant": "word",
+  "language": "cdo",
+  "unique_contexts": 308939,
+  "total_transitions": 955791
+}

models/word_markov/cdo_markov_ctx4_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e117de2ccb82cee04ee59547125507223f105436e0ac8437360575ade999d100
+size 8441712

models/word_markov/cdo_markov_ctx4_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 4,
+  "variant": "word",
+  "language": "cdo",
+  "unique_contexts": 437205,
+  "total_transitions": 939084
+}

models/word_ngram/cdo_2gram_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2869b3ed62a803296d4b64cbd8fba21a1774ee3355a39d11e555520e9c5161b
+size 191655

models/word_ngram/cdo_2gram_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 2,
+  "variant": "word",
+  "language": "cdo",
+  "unique_ngrams": 13738,
+  "total_ngrams": 989207
+}

models/word_ngram/cdo_3gram_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bfe056eb57d732812afef695d46bb07dbebf064ff917dfb6ec89e7a9cdec64d
+size 547998

models/word_ngram/cdo_3gram_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 3,
+  "variant": "word",
+  "language": "cdo",
+  "unique_ngrams": 35914,
+  "total_ngrams": 972499
+}

models/word_ngram/cdo_4gram_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9d589fedb9dc7dce0fa306987fb5585c1f152679ee6c6bf37390de81fc147cc
+size 1141850

models/word_ngram/cdo_4gram_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 4,
+  "variant": "word",
+  "language": "cdo",
+  "unique_ngrams": 75913,
+  "total_ngrams": 955791
+}