Add CHANGELOG, HuggingFace README, and upload script for v2.0

CHANGELOG.md

@@ -0,0 +1,56 @@
+# Changelog
+
+All notable changes to the Namer project will be documented in this file.
+
+## [2.0.0] - 2025-05-09
+
+### Added
+- Support for numbers up to 999,999,999,999 (trillions) - increased from 999,999
+- Stratified sampling during training for balanced representation across number scales
+- Extended max output length from 20 to 25 tokens
+- Extended max sequence length from 20 to 25 tokens
+- Special case handling for zero in inference
+- New test cases for billion and trillion ranges
+
+### Changed
+- `InfiniteNamerDataset` now uses stratified sampling by default
+- Default `max_int` changed from 999,999 to 999,999,999,999
+- Training now samples equally across: units, thousands, millions, billions, trillions
+- Model architecture unchanged but supports longer outputs
+
+### Fixed
+- Small numbers (under 1M) now work correctly with large-range model
+- Zero is now handled as a special case to prevent token repetition
+
+### Technical Details
+- Training uses 5 stratified buckets (20% each):
+  - 0-999 (units)
+  - 1,000-999,999 (thousands)
+  - 1M-999M (millions)
+  - 1B-999B (billions)
+  - 1T-999T (trillions)
+- Validation accuracy: >99.9%
+- Model parameters: ~869K
+
+## [1.0.0] - 2025-05-08
+
+### Added
+- Initial release
+- Support for numbers 0-999,999 (millions)
+- Transformer-based sequence-to-sequence model
+- HuggingFace Transformers integration
+- PyTorch native model format
+- Interactive inference mode
+- Training pipeline with infinite dataset
+
+### Features
+- 41-token vocabulary (number words + EOS)
+- 20-token max output length
+- 20-digit max input sequence length
+- 4-layer transformer encoder
+- Cross-attention mechanism with learned queries
+
+---
+
+[2.0.0]: https://github.com/edwinhere/namer/compare/v1.0.0...v2.0.0
+[1.0.0]: https://github.com/edwinhere/namer/releases/tag/v1.0.0

README_HF.md

@@ -0,0 +1,114 @@
+---
+language: en
+license: mit
+library_name: pytorch
+tags:
+  - text-generation
+  - number-to-text
+  - pytorch
+  - transformer
+  - stratified-sampling
+pipeline_tag: text-generation
+---
+
+# Namer
+
+A PyTorch transformer model that converts **integers to their English names** — now supporting numbers up to **999,999,999,999** (nearly one trillion)!
+
+## Quick Start
+
+```python
+from transformers import AutoModel
+from namer import NamerPipeline
+
+# Load model
+model = AutoModel.from_pretrained(
+    "edwinhere/namer",
+    trust_remote_code=True
+)
+
+# Create pipeline
+pipe = NamerPipeline(model)
+
+# Generate number names
+print(pipe.generate(42))                    # "forty two"
+print(pipe.generate(1234567890))            # "one billion two hundred thirty four million..."
+print(pipe.generate(999999999999))          # "nine hundred ninety nine billion..."
+```
+
+## Model Description
+
+Namer is a sequence-to-sequence transformer trained to read digits of a number and generate the corresponding English textual representation.
+
+### Key Features
+
+- 🎯 **Stratified Training**: Balanced sampling across number scales ensures accurate performance on both small and large numbers
+- 📈 **Large Range**: Handles numbers from 0 to ~1 trillion (12 digits)
+- 🚀 **Fast Inference**: Single forward pass, no autoregressive generation needed
+- 🎓 **High Accuracy**: >99.9% validation accuracy
+
+### Example Conversions
+
+| Integer | English Name |
+|---------|-------------|
+| 0 | zero |
+| 42 | forty two |
+| 123 | one hundred twenty three |
+| 1000 | one thousand |
+| 999999 | nine hundred ninety nine thousand nine hundred ninety nine |
+| 1234567890 | one billion two hundred thirty four million five hundred sixty seven thousand eight hundred ninety |
+| 999999999999 | nine hundred ninety nine billion nine hundred ninety nine million nine hundred ninety nine thousand nine hundred ninety nine |
+
+## Architecture
+
+- **Type**: Transformer encoder with learned queries and cross-attention
+- **Parameters**: ~869K
+- **Vocabulary**: 41 tokens (number words + EOS)
+- **Max Output Length**: 25 tokens
+- **Input**: Digit sequences (0-9 + padding)
+
+## Training Details
+
+- **Dataset**: Infinite stratified sampling across 5 scales (units, thousands, millions, billions, trillions)
+- **Optimizer**: Adam (lr=0.001)
+- **Epochs**: 30 with early stopping (patience=10)
+- **Hardware**: NVIDIA RTX 3070
+- **Validation Accuracy**: >99.9%
+
+### Why Stratified Sampling?
+
+With uniform random sampling from 0-1T, 99.9% of samples would be >1M, causing the model to fail on small numbers. Stratified sampling gives each magnitude equal representation (20% each), ensuring robust performance across the entire range.
+
+## Version History
+
+**v2.0 (Current)**
+- Range: 0 to 999,999,999,999 (trillions)
+- Stratified sampling for balanced training
+- Max output length: 25 tokens
+
+**v1.0**
+- Range: 0 to 999,999 (millions)
+- Uniform random sampling
+- Max output length: 20 tokens
+
+## Limitations
+
+- Maximum: 999,999,999,999 (12 digits)
+- No negative numbers (uses absolute value)
+- No decimal/fractional numbers
+
+## Citation
+
+```bibtex
+@software{namer,
+  author = {Edwin Jose Palathinkal},
+  title = {Namer: Integer to English Name Converter},
+  url = {https://huggingface.co/edwinhere/namer},
+  year = {2025}
+}
+```
+
+## Links
+
+- GitHub: https://github.com/edwinhere/namer
+- HuggingFace: https://huggingface.co/edwinhere/namer

upload.sh

@@ -0,0 +1,71 @@
+#!/bin/bash
+# Upload script for Namer model v2.0
+# This script pushes the updated model to GitHub and HuggingFace
+
+set -e
+
+echo "=== Namer v2.0 Upload Script ==="
+echo ""
+
+# Colors for output
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+NC='\033[0m' # No Color
+
+# Step 1: Verify files exist
+echo -e "${YELLOW}Step 1: Verifying files...${NC}"
+required_files=("README.md" "CHANGELOG.md" "config.json" "model.safetensors" "modeling_namer.py" "namer_model.pt")
+for file in "${required_files[@]}"; do
+    if [ ! -f "$file" ]; then
+        echo "ERROR: Required file '$file' not found!"
+        exit 1
+    fi
+    echo "  ✓ $file"
+done
+
+# Step 2: Run tests
+echo ""
+echo -e "${YELLOW}Step 2: Running tests...${NC}"
+source .venv/bin/activate
+python -m namer test
+
+# Step 3: Copy HF README
+echo ""
+echo -e "${YELLOW}Step 3: Preparing HuggingFace README...${NC}"
+cp README_HF.md README.md.tmp
+cp README.md README.md.git
+cp README_HF.md README.md
+echo "  ✓ Copied README_HF.md to README.md for HF upload"
+
+# Step 4: Commit and push to GitHub
+echo ""
+echo -e "${YELLOW}Step 4: Pushing to GitHub...${NC}"
+git add -A
+git commit -m "Namer v2.0: Support for trillions with stratified training
+
+- Extended range from millions to trillions (0-999,999,999,999)
+- Added stratified sampling for balanced training across scales
+- Increased max_output_len from 20 to 25 tokens
+- Updated documentation and added CHANGELOG
+- All tests passing"
+git push origin main
+echo "  ✓ Pushed to GitHub"
+
+# Step 5: Push to HuggingFace
+echo ""
+echo -e "${YELLOW}Step 5: Pushing to HuggingFace...${NC}"
+git push hf main
+echo "  ✓ Pushed to HuggingFace"
+
+# Step 6: Restore GitHub README
+echo ""
+echo -e "${YELLOW}Step 6: Restoring GitHub README...${NC}"
+mv README.md.tmp README.md
+echo "  ✓ Restored"
+
+echo ""
+echo -e "${GREEN}=== Upload Complete! ===${NC}"
+echo ""
+echo "Model is now available at:"
+echo "  - GitHub: https://github.com/edwinhere/namer"
+echo "  - HuggingFace: https://huggingface.co/edwinhere/namer"