Upload all models and assets for avk (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 +1,584 @@
+---
+language: avk
+language_name: AVK
+language_family: constructed_other
+tags:
+  - wikilangs
+  - nlp
+  - tokenizer
+  - embeddings
+  - n-gram
+  - markov
+  - wikipedia
+  - monolingual
+  - family-constructed_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: 4.125
+  - name: best_isotropy
+    type: isotropy
+    value: 0.8585
+  - name: vocabulary_size
+    type: vocab
+    value: 60886
+generated: 2025-12-27
+---
+
+# AVK - Wikilangs Models
+## Comprehensive Research Report & Full Ablation Study
+
+This repository contains NLP models trained and evaluated by Wikilangs, specifically on **AVK** 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 |
+|------------|-------------|---------------|----------|--------------|
+| **8k** | 3.392x | 3.33 | 0.1692% | 332,130 |
+| **16k** | 3.661x | 3.60 | 0.1827% | 307,678 |
+| **32k** | 3.908x | 3.84 | 0.1950% | 288,266 |
+| **64k** | 4.125x 🏆 | 4.06 | 0.2058% | 273,051 |
+
+### Tokenization Examples
+
+Below are sample sentences tokenized with each vocabulary size:
+
+**Sample 1:** `Loma:TezaLoma:Rovulegan liwot`
+
+| Vocab | Tokens | Count |
+|-------|--------|-------|
+| 8k | `▁loma : te zal oma : rov ul eg an ... (+1 more)` | 11 |
+| 16k | `▁loma : tezaloma : rov ul eg an ▁liwot` | 9 |
+| 32k | `▁loma : tezaloma : rovulegan ▁liwot` | 6 |
+| 64k | `▁loma : tezaloma : rovulegan ▁liwot` | 6 |
+
+**Sample 2:** `Bifa 
+ Afrika 
+
+ Amerika 
+
+ Asia 
+
+ Europa 
+
+ Oceania 
+
+ Koblira 
+
+ Awalkera 
+
+L...`
+
+| Vocab | Tokens | Count |
+|-------|--------|-------|
+| 8k | `▁bifa ▁afrika ▁amerika ▁asia ▁europa ▁oceania ▁koblira ▁awalkera ▁loma : ... (+7 more)` | 17 |
+| 16k | `▁bifa ▁afrika ▁amerika ▁asia ▁europa ▁oceania ▁koblira ▁awalkera ▁loma : ... (+7 more)` | 17 |
+| 32k | `▁bifa ▁afrika ▁amerika ▁asia ▁europa ▁oceania ▁koblira ▁awalkera ▁loma : ... (+7 more)` | 17 |
+| 64k | `▁bifa ▁afrika ▁amerika ▁asia ▁europa ▁oceania ▁koblira ▁awalkera ▁loma : ... (+7 more)` | 17 |
+
+**Sample 3:** `Bifa 
+ Afrika 
+
+ Amerika 
+
+ Asia 
+
+ Europa 
+
+ Oceania 
+
+ Koblira 
+
+ Awalkera 
+
+L...`
+
+| Vocab | Tokens | Count |
+|-------|--------|-------|
+| 8k | `▁bifa ▁afrika ▁amerika ▁asia ▁europa ▁oceania ▁koblira ▁awalkera ▁loma : ... (+6 more)` | 16 |
+| 16k | `▁bifa ▁afrika ▁amerika ▁asia ▁europa ▁oceania ▁koblira ▁awalkera ▁loma : ... (+6 more)` | 16 |
+| 32k | `▁bifa ▁afrika ▁amerika ▁asia ▁europa ▁oceania ▁koblira ▁awalkera ▁loma : ... (+6 more)` | 16 |
+| 64k | `▁bifa ▁afrika ▁amerika ▁asia ▁europa ▁oceania ▁koblira ▁awalkera ▁loma : ... (+6 more)` | 16 |
+
+
+### Key Findings
+
+- **Best Compression:** 64k achieves 4.125x compression
+- **Lowest UNK Rate:** 8k with 0.1692% 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** | 3,356 🏆 | 11.71 | 88,920 | 38.8% | 64.9% |
+| **2-gram** | 346 🏆 | 8.43 | 4,094 | 58.9% | 99.3% |
+| **3-gram** | 6,742 | 12.72 | 180,799 | 34.6% | 57.5% |
+| **3-gram** | 2,400 | 11.23 | 30,298 | 24.5% | 70.5% |
+| **4-gram** | 13,085 | 13.68 | 334,115 | 31.4% | 50.6% |
+| **4-gram** | 8,768 | 13.10 | 165,638 | 16.2% | 48.8% |
+
+### Top 5 N-grams by Size
+
+**2-grams:**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `vuest -` | 137,464 |
+| 2 | `) vuest` | 137,409 |
+| 3 | `- :` | 137,400 |
+| 4 | `( en` | 136,694 |
+| 5 | `en )` | 126,393 |
+
+**3-grams:**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `) vuest -` | 137,409 |
+| 2 | `vuest - :` | 137,400 |
+| 3 | `en ) vuest` | 124,379 |
+| 4 | `( en )` | 123,735 |
+| 5 | `) ( en` | 67,196 |
+
+**4-grams:**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `) vuest - :` | 137,400 |
+| 2 | `en ) vuest -` | 124,379 |
+| 3 | `( en ) vuest` | 121,727 |
+| 4 | `) ( en )` | 54,244 |
+| 5 | `species of the world` | 25,857 |
+
+
+### Key Findings
+
+- **Best Perplexity:** 2-gram with 346
+- **Entropy Trend:** Decreases with larger n-grams (more predictable)
+- **Coverage:** Top-1000 patterns cover ~49% 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** | 0.7348 | 1.664 | 4.95 | 126,229 | 26.5% |
+| **1** | 1.1169 | 2.169 | 9.23 | 906 | 0.0% |
+| **2** | 0.3179 | 1.247 | 1.83 | 623,886 | 68.2% |
+| **2** | 1.0082 | 2.011 | 6.31 | 8,363 | 0.0% |
+| **3** | 0.1523 | 1.111 | 1.34 | 1,136,410 | 84.8% |
+| **3** | 0.8558 | 1.810 | 4.58 | 52,772 | 14.4% |
+| **4** | 0.1022 🏆 | 1.073 | 1.23 | 1,523,485 | 89.8% |
+| **4** | 0.7129 🏆 | 1.639 | 3.05 | 241,547 | 28.7% |
+
+### Generated Text Samples
+
+Below are text samples generated from each Markov chain model:
+
+**Context Size 1:**
+
+1. `( kishida , 1814 taneon zo pimtayar . vincent van gogh nederlandaf lingesik bak muvugal ,`
+2. `) vuest - : prionailurus bengalensis ( ukraina gan wagner , fr ) ( kotava winugaf`
+3. `: pteropus temminckii temminckii ) vuest - : crocidura mariquensis shortridgei ) vuest - align :`
+
+**Context Size 2:**
+
+1. `vuest - : catalogue of life web project : macrotus waterhousii waterhousii ( gray , 1863 )`
+2. `) vuest - : uicn : katca dymecodon pilirostris ) dene wikispecies kotavafa vuestesa xantaza kotava w...`
+3. `- : itis : caracal caracal ) ( en , fr ) vuest - : alan p`
+
+**Context Size 3:**
+
+1. `) vuest - : tree of life web project : rattus palmarum ( zelebor , 1869 ) (`
+2. `vuest - : uicn : katca penthetor lucasi ( dobson , 1880 ) elmol ( dymecodon pilirostris )`
+3. `en ) vuest - : paleobiology database : thomomys bottae nanus ( hall , 1941 ) ratsikisol (`
+
+**Context Size 4:**
+
+1. `) vuest - : ncbi : simias ara vuestexa tekudol ( nasalis larvatus ) dene wikispecies kotavafa vueste...`
+2. `en ) vuest - : tree of life web project : sorex trowbridgii ( en ) vuest - :`
+3. `( en ) vuest - : tree of life web project : aepyceros melampus rendilis ( lönnberg , 1912`
+
+
+### Key Findings
+
+- **Best Predictability:** Context-4 with 89.8% predictability
+- **Branching Factor:** Decreases with context size (more deterministic)
+- **Memory Trade-off:** Larger contexts require more storage (241,547 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 | 60,886 |
+| Total Tokens | 4,116,931 |
+| Mean Frequency | 67.62 |
+| Median Frequency | 6 |
+| Frequency Std Dev | 1162.11 |
+
+### Most Common Words
+
+| Rank | Word | Frequency |
+|------|------|-----------|
+| 1 | en | 140,161 |
+| 2 | vuest | 137,464 |
+| 3 | ke | 96,689 |
+| 4 | of | 56,680 |
+| 5 | tir | 40,544 |
+| 6 | is | 40,292 |
+| 7 | va | 36,873 |
+| 8 | katca | 36,170 |
+| 9 | koe | 30,224 |
+| 10 | bak | 28,949 |
+
+### Least Common Words (from vocabulary)
+
+| Rank | Word | Frequency |
+|------|------|-----------|
+| 1 | tageltaf | 2 |
+| 2 | l4 | 2 |
+| 3 | l5 | 2 |
+| 4 | l6 | 2 |
+| 5 | l8 | 2 |
+| 6 | fakaf | 2 |
+| 7 | docs | 2 |
+| 8 | 814359978 | 2 |
+| 9 | rozuxa | 2 |
+| 10 | eaksat | 2 |
+
+### Zipf's Law Analysis
+
+| Metric | Value |
+|--------|-------|
+| Zipf Coefficient | 1.1598 |
+| R² (Goodness of Fit) | 0.995097 |
+| Adherence Quality | **excellent** |
+
+### Coverage Analysis
+
+| Top N Words | Coverage |
+|-------------|----------|
+| Top 100 | 46.2% |
+| Top 1,000 | 71.1% |
+| Top 5,000 | 86.2% |
+| Top 10,000 | 91.0% |
+
+### Key Findings
+
+- **Zipf Compliance:** R²=0.9951 indicates excellent adherence to Zipf's law
+- **High Frequency Dominance:** Top 100 words cover 46.2% of corpus
+- **Long Tail:** 50,886 words needed for remaining 9.0% 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** | 50,177 | 32 | 5.680 | 1.138 | 0.8585 🏆 |
+| **mono_64d** | 50,177 | 64 | 6.303 | 1.051 | 0.8386 |
+| **mono_128d** | 50,177 | 128 | 6.840 | 0.972 | 0.7221 |
+| **embeddings_enhanced** | 0 | 0 | 0.000 | 0.000 | 0.0000 |
+
+### Key Findings
+
+- **Best Isotropy:** mono_32d with 0.8585 (more uniform distribution)
+- **Dimension Trade-off:** Higher dimensions capture more semantics but reduce isotropy
+- **Vocabulary Coverage:** All models cover 50,177 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 (4.13x) with low UNK rate |
+| N-gram | **5-gram** | Lowest perplexity (346) |
+| Markov | **Context-4** | Highest predictability (89.8%) |
+| 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: 2025-12-27 20:44:59*

models/embeddings/monolingual/avk_128d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c77e9b8ba1437da33f48cdca5b862658b27db7a2b928bd457484eca03247babd
+size 1076298214

models/embeddings/monolingual/avk_128d.meta.json

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

models/embeddings/monolingual/avk_128d_metadata.json

@@ -0,0 +1,13 @@
+{
+  "language": "avk",
+  "dimension": 128,
+  "version": "monolingual",
+  "training_params": {
+    "dim": 128,
+    "min_count": 5,
+    "window": 5,
+    "negative": 5,
+    "epochs": 5
+  },
+  "vocab_size": 50177
+}

models/embeddings/monolingual/avk_32d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5694b8179c04c88002b40e6c2183367753202e5fa90e012bef7f5d39cfc1b2cf
+size 269762278

models/embeddings/monolingual/avk_32d.meta.json

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

models/embeddings/monolingual/avk_32d_metadata.json

@@ -0,0 +1,13 @@
+{
+  "language": "avk",
+  "dimension": 32,
+  "version": "monolingual",
+  "training_params": {
+    "dim": 32,
+    "min_count": 5,
+    "window": 5,
+    "negative": 5,
+    "epochs": 5
+  },
+  "vocab_size": 50177
+}

models/embeddings/monolingual/avk_64d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7dc9c61284134af30b4d1b2aab6224be3afd4e9f49b2a64ed0c40abc179bcfa
+size 538607590

models/embeddings/monolingual/avk_64d.meta.json

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

models/embeddings/monolingual/avk_64d_metadata.json

@@ -0,0 +1,13 @@
+{
+  "language": "avk",
+  "dimension": 64,
+  "version": "monolingual",
+  "training_params": {
+    "dim": 64,
+    "min_count": 5,
+    "window": 5,
+    "negative": 5,
+    "epochs": 5
+  },
+  "vocab_size": 50177
+}

models/subword_markov/avk_markov_ctx1_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c87d050968fb890ac14fd71d59704c1f20be0cade22594a02304808593949be
+size 72153

models/subword_markov/avk_markov_ctx1_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 1,
+  "variant": "subword",
+  "language": "avk",
+  "unique_contexts": 906,
+  "total_transitions": 31142755
+}

models/subword_markov/avk_markov_ctx2_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8f446b4ef71a4c8448a34fa74f0f82934b9a8860a62763f7de0514ccfd67de8
+size 477700

models/subword_markov/avk_markov_ctx2_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 2,
+  "variant": "subword",
+  "language": "avk",
+  "unique_contexts": 8363,
+  "total_transitions": 31112980
+}

models/subword_markov/avk_markov_ctx3_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30469dc41cdc5cdb5c2b8b6b30f354558cbbf809a10ce1a41cb209d02349b970
+size 1961477

models/subword_markov/avk_markov_ctx3_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 3,
+  "variant": "subword",
+  "language": "avk",
+  "unique_contexts": 52772,
+  "total_transitions": 31083205
+}

models/subword_markov/avk_markov_ctx4_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d2a2dc2ccd788db6d4fe7dc4b501e476474e463f9b5daf894e7bc60a3807863
+size 6015167

models/subword_markov/avk_markov_ctx4_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 4,
+  "variant": "subword",
+  "language": "avk",
+  "unique_contexts": 241547,
+  "total_transitions": 31053430
+}

models/subword_ngram/avk_2gram_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57623fd2d7680170fb70b8a54a85080d046adabcb09f6ba248e51ab954c23704
+size 58053

models/subword_ngram/avk_2gram_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 2,
+  "variant": "subword",
+  "language": "avk",
+  "unique_ngrams": 4094,
+  "total_ngrams": 31142755
+}

models/subword_ngram/avk_3gram_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19dd489abd0754a69d92d86b3d70f88fb08a90407bbf8d44bfe8e11b8162b8a8
+size 400583

models/subword_ngram/avk_3gram_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 3,
+  "variant": "subword",
+  "language": "avk",
+  "unique_ngrams": 30298,
+  "total_ngrams": 31112980
+}

models/subword_ngram/avk_4gram_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e008f4e015b488a0806b82114bc302e1ba6408d9dba61c412e1b9c744997da9e
+size 1909769

models/subword_ngram/avk_4gram_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 4,
+  "variant": "subword",
+  "language": "avk",
+  "unique_ngrams": 165638,
+  "total_ngrams": 31083205
+}

models/tokenizer/avk_tokenizer_16k.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9c55784109e43a9432c17273e8dd91088994ff7e64a334adde79a110fa50a78
+size 508877

models/tokenizer/avk_tokenizer_32k.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71b9f51b6fde0ce3af71bf329e3a16fab1dbe74661cb0d5e5795706d4346ef3
+size 787205

models/tokenizer/avk_tokenizer_64k.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:592345fe0811d55c932390e43251d8f96797fc431da7b02804fa98e5b8b37b49
+size 1365457

models/tokenizer/avk_tokenizer_8k.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ef85dbb33d9d8d185ae20f51d9e408ef65f997f3f54be0cc29a91476ae2b6b
+size 372682

models/vocabulary/avk_vocabulary.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9badd3be683b3de4d818a068b65f846f74b9b2c821667b9ee89e8ff9dfd1c380
+size 1067310

models/vocabulary/avk_vocabulary_metadata.json

@@ -0,0 +1,16 @@
+{
+  "language": "avk",
+  "vocabulary_size": 60886,
+  "statistics": {
+    "type_token_ratio": 0.03016752857100501,
+    "coverage": {
+      "top_100": 0.45497789208198913,
+      "top_1000": 0.6999908182559851,
+      "top_5000": 0.8483328917807131,
+      "top_10000": 0.8961334336948964
+    },
+    "hapax_count": 65281,
+    "hapax_ratio": 0.5174173912354261,
+    "total_documents": 29775
+  }
+}

models/word_markov/avk_markov_ctx1_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45daf4d90b1c151ceeaf2eafabe0c4eb0fa4f302b0586de0d0c7c9828132282f
+size 5408930

models/word_markov/avk_markov_ctx1_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 1,
+  "variant": "word",
+  "language": "avk",
+  "unique_contexts": 126229,
+  "total_transitions": 6480020
+}

models/word_markov/avk_markov_ctx2_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:490cc4a34315fffeeafc0bb6770bd3f6596968d38e894a020c7de5de669ad396
+size 12552041

models/word_markov/avk_markov_ctx2_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 2,
+  "variant": "word",
+  "language": "avk",
+  "unique_contexts": 623886,
+  "total_transitions": 6450251
+}

models/word_markov/avk_markov_ctx3_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65c7f7d50c4f9d2ab9884a6416fce5a63b12d44a814648773af5258e5bdca88c
+size 18746428

models/word_markov/avk_markov_ctx3_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 3,
+  "variant": "word",
+  "language": "avk",
+  "unique_contexts": 1136410,
+  "total_transitions": 6420500
+}

models/word_markov/avk_markov_ctx4_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb6d9225de08c55bad0b5b1c52937c5a7af6b67625fbe4a58d094126e4da419d
+size 24304336

models/word_markov/avk_markov_ctx4_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 4,
+  "variant": "word",
+  "language": "avk",
+  "unique_contexts": 1523485,
+  "total_transitions": 6390750
+}

models/word_ngram/avk_2gram_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0be3cc4f49219f8041292992a9db6978b8873a52d64b4d15b2db6d55a0194adb
+size 1119286

models/word_ngram/avk_2gram_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 2,
+  "variant": "word",
+  "language": "avk",
+  "unique_ngrams": 88920,
+  "total_ngrams": 6480020
+}

models/word_ngram/avk_3gram_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2399a2f98604cf3b9e3bceaee6ac55b8f98eedfafb4ece0a8e26bf3ee2a0fb04
+size 2239472

models/word_ngram/avk_3gram_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 3,
+  "variant": "word",
+  "language": "avk",
+  "unique_ngrams": 180799,
+  "total_ngrams": 6450251
+}

models/word_ngram/avk_4gram_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cddb3b457d830002d6f39a4845d76b1095745537a700a6adf4d1c7fe8365ea85
+size 4190267

models/word_ngram/avk_4gram_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 4,
+  "variant": "word",
+  "language": "avk",
+  "unique_ngrams": 334115,
+  "total_ngrams": 6420500
+}