Upload README.md with huggingface_hub

README.md

@@ -14,7 +14,7 @@ datasets:
 - Nexuss0781/synaxarium
 - Nexuss0781/conon-biblical-am-en
 metrics:
-- perfect-reconstruction
+- reconstruction-accuracy
 widget:
 - text: "ሰላም ለኢዮብ ዘኢነበበ ከንቶ ።"
 ---
@@ -25,17 +25,24 @@ widget:
 [![Hugging Face](https://img.shields.io/badge/🤗-Hugging_Face-yellow)](https://huggingface.co/Nexuss0781/Ethio-BBPE)
 [![Amharic](https://img.shields.io/badge/Language-Amharic-green.svg)](https://en.wikipedia.org/wiki/Amharic)
 [![Tokenizer Type](https://img.shields.io/badge/Type-Byte--level_BPE-orange.svg)](https://huggingface.co/docs/tokenizers/index)
+[![GitHub](https://img.shields.io/badge/GitHub-repo-blue)](https://github.com/nexuss0781/Ethio_BBPE)
 
-A production-ready **Byte-level BPE tokenizer** specifically trained on **Amharic biblical and religious texts**, achieving **perfect reconstruction** of complex Ge'ez script, ancient punctuation, and liturgical content.
+A production-ready **Byte-level BPE tokenizer** specifically trained on **Amharic biblical and religious texts**, achieving **accurate reconstruction** of complex Ge'ez script, ancient punctuation, and liturgical content.
 
 ## ✨ Features
 
-- ✅ **Perfect Reconstruction**: 100% accuracy on all test samples including ancient Ge'ez punctuation
+- ✅ **Accurate Reconstruction**: High accuracy on all test samples including ancient Ge'ez punctuation
 - ✅ **Specialized Vocabulary**: Trained on 61,769 lines of Amharic biblical texts (Synaxarium + Canon Bible)
 - ✅ **Compressed Storage**: Gzip compression (level 9) reduces model size by **89.8%** (1.3MB → 136KB)
 - ✅ **Production Ready**: Checkpointing, metrics tracking, and comprehensive error handling
 - ✅ **Ge'ez Script Support**: Full support for Ethiopic characters, numerals, and liturgical punctuation marks
 
+## 🔗 Resources
+
+- **Source Code**: [GitHub Repository](https://github.com/nexuss0781/Ethio_BBPE)
+- **Issue Tracker**: [GitHub Issues](https://github.com/nexuss0781/Ethio_BBPE/issues)
+- **PyPI Package**: [EthioBBPE on PyPI](https://pypi.org/project/EthioBBPE/)
+
 ## 📊 Training Data
 
 | Dataset | Source | Texts | Description |
@@ -61,10 +68,10 @@ A production-ready **Byte-level BPE tokenizer** specifically trained on **Amhari
 
 | Metric | Result |
 |--------|--------|
-| **Perfect Reconstruction** | ✅ **100%** |
-| **Ge'ez Punctuation** | ✅ Perfect (1 token for `፠፠፠፠፠፠፠፠፠፠፠፠፠፠፠፠፠፠`) |
-| **Synaxarium Text** | ✅ Perfect (66 tokens) |
-| **Biblical Text** | ✅ Perfect (82 tokens) |
+| **Accurate Reconstruction** | ✅ High accuracy |
+| **Ge'ez Punctuation** | ✅ Accurate (1 token for `፠፠፠፠፠፠፠፠፠፠፠፠፠፠፠፠፠፠`) |
+| **Synaxarium Text** | ✅ Accurate (66 tokens) |
+| **Biblical Text** | ✅ Accurate (82 tokens) |
 | **Compression Ratio** | **89.8%** (1.3MB → 136KB) |
 | **Training Time** | ~17 seconds |
 
@@ -189,7 +196,7 @@ for i, enc in enumerate(encodings):
 
 ## 🧪 Testing & Validation
 
-All test cases achieve **perfect reconstruction**:
+All test cases achieve **accurate reconstruction**:
 
 ```python
 test_cases = [
@@ -202,7 +209,7 @@ for name, text in test_cases:
     encoded = tokenizer.encode(text)
     decoded = tokenizer.decode(encoded.ids)
     assert text == decoded, f"{name} failed!"
-    print(f"✅ {name}: Perfect ({len(encoded.ids)} tokens)")
+    print(f"✅ {name}: Accurate ({len(encoded.ids)} tokens)")
 ```
 
 ## 📚 Datasets
@@ -247,6 +254,7 @@ Apache License 2.0 - See [LICENSE](LICENSE) for details.
 
 - **GitHub**: [nexuss0781/Ethio_BBPE](https://github.com/nexuss0781/Ethio_BBPE)
 - **Hugging Face**: [Nexuss0781/Ethio-BBPE](https://huggingface.co/Nexuss0781/Ethio-BBPE)
+- **PyPI**: [EthioBBPE Package](https://pypi.org/project/EthioBBPE/)
 - **Issues**: Please open an issue on GitHub for bugs or feature requests
 
 ---