gptmed 0.0.1__tar.gz

gptmed-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Your Name
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

gptmed-0.0.1/MANIFEST.in

@@ -0,0 +1,40 @@
+# Include documentation
+include README.md
+include LICENSE
+include requirements.txt
+
+# Include configuration files
+recursive-include configs *.py *.json *.yaml
+
+# Include model configs
+recursive-include model/configs *.py *.json
+
+# Include tokenizer files (vocab and model files)
+recursive-include tokenizer *.model *.vocab *.json
+
+# Exclude unnecessary files
+exclude .gitignore
+exclude .env
+exclude *.pyc
+exclude */__pycache__/*
+recursive-exclude * __pycache__
+recursive-exclude * *.py[co]
+recursive-exclude * .DS_Store
+
+# Exclude datasets, logs, and checkpoints (too large for PyPI)
+exclude dataset/*
+exclude logs/*
+exclude model/checkpoints/*
+recursive-exclude dataset *
+recursive-exclude logs *
+recursive-exclude model/checkpoints *
+
+# Exclude test files
+recursive-exclude tests *
+exclude test_*.py
+
+# Exclude development/training scripts not needed for inference
+exclude download_medquad.py
+exclude monitor_training.py
+exclude preprocess.py
+exclude generate_sample.py

gptmed-0.0.1/PKG-INFO

@@ -0,0 +1,325 @@
+Metadata-Version: 2.4
+Name: gptmed
+Version: 0.0.1
+Summary: A lightweight GPT-based language model framework for training custom question-answering models on any domain
+Author-email: Sanjog Sigdel <sigdelsanjog@gmail.com>
+Maintainer-email: Sanjog Sigdel <sigdelsanjog@gmail.com>
+License: MIT License
+        
+        Copyright (c) 2026 Your Name
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
+Project-URL: Homepage, https://github.com/sigdelsanjog/gptmed
+Project-URL: Documentation, https://github.com/sigdelsanjog/gptmed#readme
+Project-URL: Repository, https://github.com/sigdelsanjog/gptmed
+Project-URL: Issues, https://github.com/sigdelsanjog/gptmed/issues
+Keywords: nlp,language-model,transformer,gpt,pytorch,qa,question-answering,training,deep-learning,custom-model
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: Education
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch>=2.0.0
+Requires-Dist: sentencepiece>=0.1.99
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: tqdm>=4.65.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: black>=22.0.0; extra == "dev"
+Requires-Dist: flake8>=4.0.0; extra == "dev"
+Requires-Dist: mypy>=0.950; extra == "dev"
+Provides-Extra: training
+Requires-Dist: tensorboard>=2.10.0; extra == "training"
+Requires-Dist: wandb>=0.13.0; extra == "training"
+Dynamic: license-file
+
+# GptMed 🤖
+
+A lightweight GPT-based language model framework for training custom question-answering models on any domain. This package provides a transformer-based GPT architecture that you can train on your own Q&A datasets - whether it's casual conversations, technical support, education, or any other domain.
+
+[![PyPI version](https://badge.fury.io/py/gptmed.svg)](https://badge.fury.io/py/gptmed)
+[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+## Features
+
+- 🧠 **Custom GPT Architecture**: Lightweight transformer model for any Q&A domain
+- 🎯 **Domain-Agnostic**: Train on any question-answering dataset (casual chat, tech support, education, etc.)
+- ⚡ **Fast Inference**: Optimized for quick question answering
+- 🔧 **Flexible Training**: Easy to train on your own custom datasets
+- 📦 **Lightweight**: Small model size suitable for edge deployment
+- 🛠️ **Complete Toolkit**: Includes tokenizer training, model training, and inference utilities
+
+## Installation
+
+### From PyPI (Recommended)
+
+```bash
+pip install gptmed
+```
+
+### From Source
+
+```bash
+git clone https://github.com/sigdelsanjog/gptmed.git
+cd gptmed
+pip install -e .
+```
+
+### With Optional Dependencies
+
+```bash
+# For development
+pip install gptmed[dev]
+
+# For training
+pip install gptmed[training]
+
+# All dependencies
+pip install gptmed[dev,training]
+```
+
+## Quick Start
+
+### Inference (Generate Answers)
+
+```python
+from gptmed.inference.generator import TextGenerator
+from gptmed.model.architecture import GPTTransformer
+from gptmed.model.configs.model_config import get_small_config
+
+# Load model
+config = get_small_config()
+model = GPTTransformer(config)
+
+# Load your trained checkpoint
+# model.load_state_dict(torch.load('path/to/checkpoint.pt'))
+
+# Create generator
+generator = TextGenerator(
+    model=model,
+    tokenizer_path='path/to/tokenizer.model'
+)
+
+# Generate answer
+question = "What's your favorite programming language?"
+answer = generator.generate(
+    prompt=question,
+    max_length=100,
+    temperature=0.7
+)
+
+print(f"Q: {question}")
+print(f"A: {answer}")
+```
+
+### Using Command Line
+
+```bash
+# Generate answers
+gptmed-generate --prompt "How do I train a custom model?" --max-length 100
+
+# Train model
+gptmed-train --model-size small --num-epochs 10 --batch-size 16
+```
+
+### Training Your Own Model
+
+```python
+from gptmed.training.train import main
+from gptmed.configs.train_config import get_default_config
+from gptmed.model.configs.model_config import get_small_config
+
+# Configure training
+train_config = get_default_config()
+train_config.batch_size = 16
+train_config.num_epochs = 10
+train_config.learning_rate = 3e-4
+
+# Start training
+main()
+```
+
+## Model Architecture
+
+The model uses a custom GPT-based transformer architecture:
+
+- **Embedding**: Token + positional embeddings
+- **Transformer Blocks**: Multi-head self-attention + feed-forward networks
+- **Parameters**: ~10M (small), ~50M (medium)
+- **Context Length**: 512 tokens
+- **Vocabulary**: Custom SentencePiece tokenizer trained on your data
+
+## Configuration
+
+### Model Sizes
+
+```python
+from gptmed.model.configs.model_config import (
+    get_tiny_config,   # ~2M parameters - for testing
+    get_small_config,  # ~10M parameters - recommended
+    get_medium_config  # ~50M parameters - higher quality
+)
+```
+
+### Training Configuration
+
+```python
+from gptmed.configs.train_config import TrainingConfig
+
+config = TrainingConfig(
+    batch_size=16,
+    learning_rate=3e-4,
+    num_epochs=10,
+    warmup_steps=100,
+    grad_clip=1.0
+)
+```
+
+## Project Structure
+
+```
+gptmed/
+├── model/
+│   ├── architecture/      # GPT transformer implementation
+│   └── configs/           # Model configurations
+├── inference/
+│   ├── generator.py       # Text generation
+│   └── sampling.py        # Sampling strategies
+├── training/
+│   ├── train.py          # Training script
+│   ├── trainer.py        # Training loop
+│   └── dataset.py        # Data loading
+├── tokenizer/
+│   └── train_tokenizer.py # SentencePiece tokenizer
+├── configs/
+│   └── train_config.py   # Training configurations
+└── utils/
+    ├── checkpoints.py    # Model checkpointing
+    └── logging.py        # Training logging
+```
+
+## Requirements
+
+- Python >= 3.8
+- PyTorch >= 2.0.0
+- sentencepiece >= 0.1.99
+- numpy >= 1.24.0
+- tqdm >= 4.65.0
+
+## Documentation
+
+For detailed documentation, visit [GitHub Repository](https://github.com/yourusername/medllm).
+
+### Key Guides
+
+- [Training Guide](docs/training.md)
+- [Inference Guide](docs/inference.md)
+- [Model Architecture](docs/architecture.md)
+- [API Reference](docs/api.md)
+
+## Performance
+
+| Model Size | Parameters | Training Time | Inference Speed |
+| ---------- | ---------- | ------------- | --------------- |
+| Tiny       | ~2M        | 2 hours       | ~100 tokens/sec |
+| Small      | ~10M       | 8 hours       | ~80 tokens/sec  |
+| Medium     | ~50M       | 24 hours      | ~50 tokens/sec  |
+
+_Tested on GTX 1080 8GB_
+
+## Examples
+
+### Medical Question Answering
+
+```python
+# Example 1: Symptoms inquiry
+question = "What are the early signs of Alzheimer's disease?"
+answer = generator.generate(question, temperature=0.7)
+
+# Example 2: Treatment information
+question = "How is Type 2 diabetes treated?"
+answer = generator.generate(question, temperature=0.6)
+
+# Example 3: Medical definitions
+question = "What is hypertension?"
+answer = generator.generate(question, temperature=0.5)
+```
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+1. Fork the repository
+2. Create your feature branch (`git checkout -b feature/AmazingFeature`)
+3. Commit your changes (`git commit -m 'Add some AmazingFeature'`)
+4. Push to the branch (`git push origin feature/AmazingFeature`)
+5. Open a Pull Request
+
+## Citation
+
+If you use this model in your research, please cite:
+
+```bibtex
+@software{llm_med_2026,
+  author = {Sanjog Sigdel},
+  title = {GptMed: A custom causal question answering general purpose GPT Transformer Architecture Model},
+  year = {2026},
+  url = {https://github.com/sigdelsanjog/gptmed}
+}
+```
+
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## Acknowledgments
+
+- MedQuAD dataset creators
+- PyTorch team
+
+## Disclaimer
+
+⚠️ **Medical Disclaimer**: This model is for research and educational purposes only. It should NOT be used for actual medical diagnosis or treatment decisions. Always consult qualified healthcare professionals for medical advice.
+
+## Support
+
+- 📫 Issues: [GitHub Issues](https://github.com/sigdelsanjog/gptmed/issues)
+- 💬 Discussions: [GitHub Discussions](https://github.com/sigdelsanjog/gptmed/discussions)
+- 📧 Email: sanjog.sigdel@ku.edu.np
+
+## Changelog
+
+See [CHANGELOG.md](CHANGELOG.md) for version history.
+
+---
+
+Made with ❤️ for learning purpose

gptmed-0.0.1/README.md

@@ -0,0 +1,262 @@
+# GptMed 🤖
+
+A lightweight GPT-based language model framework for training custom question-answering models on any domain. This package provides a transformer-based GPT architecture that you can train on your own Q&A datasets - whether it's casual conversations, technical support, education, or any other domain.
+
+[![PyPI version](https://badge.fury.io/py/gptmed.svg)](https://badge.fury.io/py/gptmed)
+[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+## Features
+
+- 🧠 **Custom GPT Architecture**: Lightweight transformer model for any Q&A domain
+- 🎯 **Domain-Agnostic**: Train on any question-answering dataset (casual chat, tech support, education, etc.)
+- ⚡ **Fast Inference**: Optimized for quick question answering
+- 🔧 **Flexible Training**: Easy to train on your own custom datasets
+- 📦 **Lightweight**: Small model size suitable for edge deployment
+- 🛠️ **Complete Toolkit**: Includes tokenizer training, model training, and inference utilities
+
+## Installation
+
+### From PyPI (Recommended)
+
+```bash
+pip install gptmed
+```
+
+### From Source
+
+```bash
+git clone https://github.com/sigdelsanjog/gptmed.git
+cd gptmed
+pip install -e .
+```
+
+### With Optional Dependencies
+
+```bash
+# For development
+pip install gptmed[dev]
+
+# For training
+pip install gptmed[training]
+
+# All dependencies
+pip install gptmed[dev,training]
+```
+
+## Quick Start
+
+### Inference (Generate Answers)
+
+```python
+from gptmed.inference.generator import TextGenerator
+from gptmed.model.architecture import GPTTransformer
+from gptmed.model.configs.model_config import get_small_config
+
+# Load model
+config = get_small_config()
+model = GPTTransformer(config)
+
+# Load your trained checkpoint
+# model.load_state_dict(torch.load('path/to/checkpoint.pt'))
+
+# Create generator
+generator = TextGenerator(
+    model=model,
+    tokenizer_path='path/to/tokenizer.model'
+)
+
+# Generate answer
+question = "What's your favorite programming language?"
+answer = generator.generate(
+    prompt=question,
+    max_length=100,
+    temperature=0.7
+)
+
+print(f"Q: {question}")
+print(f"A: {answer}")
+```
+
+### Using Command Line
+
+```bash
+# Generate answers
+gptmed-generate --prompt "How do I train a custom model?" --max-length 100
+
+# Train model
+gptmed-train --model-size small --num-epochs 10 --batch-size 16
+```
+
+### Training Your Own Model
+
+```python
+from gptmed.training.train import main
+from gptmed.configs.train_config import get_default_config
+from gptmed.model.configs.model_config import get_small_config
+
+# Configure training
+train_config = get_default_config()
+train_config.batch_size = 16
+train_config.num_epochs = 10
+train_config.learning_rate = 3e-4
+
+# Start training
+main()
+```
+
+## Model Architecture
+
+The model uses a custom GPT-based transformer architecture:
+
+- **Embedding**: Token + positional embeddings
+- **Transformer Blocks**: Multi-head self-attention + feed-forward networks
+- **Parameters**: ~10M (small), ~50M (medium)
+- **Context Length**: 512 tokens
+- **Vocabulary**: Custom SentencePiece tokenizer trained on your data
+
+## Configuration
+
+### Model Sizes
+
+```python
+from gptmed.model.configs.model_config import (
+    get_tiny_config,   # ~2M parameters - for testing
+    get_small_config,  # ~10M parameters - recommended
+    get_medium_config  # ~50M parameters - higher quality
+)
+```
+
+### Training Configuration
+
+```python
+from gptmed.configs.train_config import TrainingConfig
+
+config = TrainingConfig(
+    batch_size=16,
+    learning_rate=3e-4,
+    num_epochs=10,
+    warmup_steps=100,
+    grad_clip=1.0
+)
+```
+
+## Project Structure
+
+```
+gptmed/
+├── model/
+│   ├── architecture/      # GPT transformer implementation
+│   └── configs/           # Model configurations
+├── inference/
+│   ├── generator.py       # Text generation
+│   └── sampling.py        # Sampling strategies
+├── training/
+│   ├── train.py          # Training script
+│   ├── trainer.py        # Training loop
+│   └── dataset.py        # Data loading
+├── tokenizer/
+│   └── train_tokenizer.py # SentencePiece tokenizer
+├── configs/
+│   └── train_config.py   # Training configurations
+└── utils/
+    ├── checkpoints.py    # Model checkpointing
+    └── logging.py        # Training logging
+```
+
+## Requirements
+
+- Python >= 3.8
+- PyTorch >= 2.0.0
+- sentencepiece >= 0.1.99
+- numpy >= 1.24.0
+- tqdm >= 4.65.0
+
+## Documentation
+
+For detailed documentation, visit [GitHub Repository](https://github.com/yourusername/medllm).
+
+### Key Guides
+
+- [Training Guide](docs/training.md)
+- [Inference Guide](docs/inference.md)
+- [Model Architecture](docs/architecture.md)
+- [API Reference](docs/api.md)
+
+## Performance
+
+| Model Size | Parameters | Training Time | Inference Speed |
+| ---------- | ---------- | ------------- | --------------- |
+| Tiny       | ~2M        | 2 hours       | ~100 tokens/sec |
+| Small      | ~10M       | 8 hours       | ~80 tokens/sec  |
+| Medium     | ~50M       | 24 hours      | ~50 tokens/sec  |
+
+_Tested on GTX 1080 8GB_
+
+## Examples
+
+### Medical Question Answering
+
+```python
+# Example 1: Symptoms inquiry
+question = "What are the early signs of Alzheimer's disease?"
+answer = generator.generate(question, temperature=0.7)
+
+# Example 2: Treatment information
+question = "How is Type 2 diabetes treated?"
+answer = generator.generate(question, temperature=0.6)
+
+# Example 3: Medical definitions
+question = "What is hypertension?"
+answer = generator.generate(question, temperature=0.5)
+```
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+1. Fork the repository
+2. Create your feature branch (`git checkout -b feature/AmazingFeature`)
+3. Commit your changes (`git commit -m 'Add some AmazingFeature'`)
+4. Push to the branch (`git push origin feature/AmazingFeature`)
+5. Open a Pull Request
+
+## Citation
+
+If you use this model in your research, please cite:
+
+```bibtex
+@software{llm_med_2026,
+  author = {Sanjog Sigdel},
+  title = {GptMed: A custom causal question answering general purpose GPT Transformer Architecture Model},
+  year = {2026},
+  url = {https://github.com/sigdelsanjog/gptmed}
+}
+```
+
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## Acknowledgments
+
+- MedQuAD dataset creators
+- PyTorch team
+
+## Disclaimer
+
+⚠️ **Medical Disclaimer**: This model is for research and educational purposes only. It should NOT be used for actual medical diagnosis or treatment decisions. Always consult qualified healthcare professionals for medical advice.
+
+## Support
+
+- 📫 Issues: [GitHub Issues](https://github.com/sigdelsanjog/gptmed/issues)
+- 💬 Discussions: [GitHub Discussions](https://github.com/sigdelsanjog/gptmed/discussions)
+- 📧 Email: sanjog.sigdel@ku.edu.np
+
+## Changelog
+
+See [CHANGELOG.md](CHANGELOG.md) for version history.
+
+---
+
+Made with ❤️ for learning purpose

gptmed-0.0.1/gptmed/__init__.py

@@ -0,0 +1,37 @@
+"""
+llm-med: A lightweight medical question-answering language model
+
+This package provides a GPT-based transformer architecture trained on the MedQuAD dataset
+for medical domain question answering.
+
+Main Components:
+- model: GPT transformer architecture
+- inference: Text generation and sampling
+- training: Training loop and utilities
+- tokenizer: SentencePiece tokenizer
+- configs: Configuration management
+- utils: Utility functions
+
+Example:
+    >>> from llm_med.model.architecture import GPTTransformer
+    >>> from llm_med.model.configs.model_config import get_small_config
+    >>> from llm_med.inference.generator import TextGenerator
+    >>> 
+    >>> config = get_small_config()
+    >>> model = GPTTransformer(config)
+"""
+
+__version__ = "0.2.0"
+__author__ = "Sanjog Sigdel"
+__email__ = "sigdelsanjog@gmail.com"
+
+# Expose main components at package level for convenience
+from llm_med.model.architecture import GPTTransformer
+from llm_med.model.configs.model_config import ModelConfig, get_small_config, get_tiny_config
+
+__all__ = [
+    "GPTTransformer",
+    "ModelConfig",
+    "get_small_config",
+    "get_tiny_config",
+]

gptmed-0.0.1/gptmed/configs/__init__.py

@@ -0,0 +1 @@
+"""Configs package."""