langtune 0.0.2__tar.gz → 0.0.3__tar.gz

{langtune-0.0.2/src/langtune.egg-info → langtune-0.0.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: langtune
-Version: 0.0.2
+Version: 0.0.3
 Summary: A package for finetuning text models.
 Author-email: Pritesh Raj <priteshraj41@gmail.com>
 License: MIT License
@@ -39,7 +39,7 @@ Requires-Dist: pyyaml
 Requires-Dist: scipy
 Dynamic: license-file
 
-# Langtune: Large Language Models (LLMs) with Efficient LoRA Fine-Tuning for Text
+# Langtune: Efficient LoRA Fine-Tuning for Text LLMs
 
 <hr/>
 <p align="center">
@@ -60,8 +60,8 @@ Dynamic: license-file
 </p>
 
 <p align="center">
-  <b>Langtune provides modular components for text models and LoRA-based fine-tuning.</b><br/>
-  <span style="font-size:1.1em"><i>Adapt and fine-tune language models for a range of NLP tasks.</i></span>
+  <b>Langtune is a Python package for fine-tuning large language models on text data using LoRA.</b><br/>
+  <span style="font-size:1.1em"><i>Provides modular components for adapting language models to various NLP tasks.</i></span>
 </p>
 <hr/>
 
@@ -89,41 +89,40 @@ Dynamic: license-file
 - [Examples & Use Cases](#examples--use-cases)
 - [Extending the Framework](#extending-the-framework)
 - [Contributing](#contributing)
-- [FAQ](#faq)
+- [License](#license)
 - [Citation](#citation)
 - [Acknowledgements](#acknowledgements)
-- [License](#license)
 
 ---
 
 ## Features
-- LoRA adapters for parameter-efficient fine-tuning of LLMs
+- LoRA adapters for efficient fine-tuning
 - Modular transformer backbone
-- Model zoo for open-source language models
+- Model zoo for language models
 - Configurable and extensible codebase
-- Checkpointing and resume support
+- Checkpointing and resume
 - Mixed precision and distributed training
-- Built-in metrics and visualization tools
-- CLI for fine-tuning and evaluation
-- Extensible callbacks (early stopping, logging, etc.)
+- Metrics and visualization tools
+- CLI for training and evaluation
+- Callback support (early stopping, logging, etc.)
 
 ---
 
 ## Showcase
 
-Langtune is a framework for building and fine-tuning large language models with LoRA support. It is suitable for tasks such as text classification, summarization, question answering, and other NLP applications.
+Langtune is intended for building and fine-tuning large language models with LoRA. It can be used for text classification, summarization, question answering, and other NLP tasks.
 
 ---
 
 ## Getting Started
 
-Install with pip:
+Install:
 
 ```bash
 pip install langtune
 ```
 
-Minimal example:
+Example usage:
 
 ```python
 import torch
@@ -145,28 +144,28 @@ with torch.no_grad():
     print('Output shape:', out.shape)
 ```
 
-For more details, see the [Documentation](docs/index.md) and `src/langtune/cli/finetune.py`.
+See the [Documentation](docs/index.md) and `src/langtune/cli/finetune.py` for more details.
 
 ---
 
 ## Supported Python Versions
-- Python 3.8+
+- Python 3.8 or newer
 
 ---
 
 ## Why langtune?
 
-- Parameter-efficient fine-tuning with LoRA adapters
-- Modular transformer backbone for flexible model design
-- Unified interface for open-source language models
-- Designed for both research and production
-- Efficient memory usage for large models
+- Fine-tuning with LoRA adapters
+- Modular transformer design
+- Unified interface for language models
+- Suitable for research and production
+- Efficient memory usage
 
 ---
 
 ## Architecture Overview
 
-Langtune uses a modular transformer backbone with LoRA adapters in attention and MLP layers. This allows adaptation of pre-trained models with fewer trainable parameters.
+Langtune uses a transformer backbone with LoRA adapters in attention and MLP layers. This enables adaptation of pre-trained models with fewer trainable parameters.
 
 ### Model Data Flow
 
@@ -337,12 +336,14 @@ model.finetune(dataset, config_path="configs/custom_config.yaml")
 - For advanced usage, see `src/langtune/cli/finetune.py`.
 
 ## Contributing
-We welcome contributions. See the [Contributing Guide](CONTRIBUTING.md) for details.
+Contributions are welcome. See the [Contributing Guide](CONTRIBUTING.md) for details.
 
-## License & Citation
+## License
 
 This project is licensed under the MIT License. See [LICENSE](LICENSE) for details.
 
+## Citation
+
 If you use langtune in your research, please cite:
 
 ```bibtex

{langtune-0.0.2 → langtune-0.0.3}/README.md

@@ -1,4 +1,4 @@
-# Langtune: Large Language Models (LLMs) with Efficient LoRA Fine-Tuning for Text
+# Langtune: Efficient LoRA Fine-Tuning for Text LLMs
 
 <hr/>
 <p align="center">
@@ -19,8 +19,8 @@
 </p>
 
 <p align="center">
-  <b>Langtune provides modular components for text models and LoRA-based fine-tuning.</b><br/>
-  <span style="font-size:1.1em"><i>Adapt and fine-tune language models for a range of NLP tasks.</i></span>
+  <b>Langtune is a Python package for fine-tuning large language models on text data using LoRA.</b><br/>
+  <span style="font-size:1.1em"><i>Provides modular components for adapting language models to various NLP tasks.</i></span>
 </p>
 <hr/>
 
@@ -48,41 +48,40 @@
 - [Examples & Use Cases](#examples--use-cases)
 - [Extending the Framework](#extending-the-framework)
 - [Contributing](#contributing)
-- [FAQ](#faq)
+- [License](#license)
 - [Citation](#citation)
 - [Acknowledgements](#acknowledgements)
-- [License](#license)
 
 ---
 
 ## Features
-- LoRA adapters for parameter-efficient fine-tuning of LLMs
+- LoRA adapters for efficient fine-tuning
 - Modular transformer backbone
-- Model zoo for open-source language models
+- Model zoo for language models
 - Configurable and extensible codebase
-- Checkpointing and resume support
+- Checkpointing and resume
 - Mixed precision and distributed training
-- Built-in metrics and visualization tools
-- CLI for fine-tuning and evaluation
-- Extensible callbacks (early stopping, logging, etc.)
+- Metrics and visualization tools
+- CLI for training and evaluation
+- Callback support (early stopping, logging, etc.)
 
 ---
 
 ## Showcase
 
-Langtune is a framework for building and fine-tuning large language models with LoRA support. It is suitable for tasks such as text classification, summarization, question answering, and other NLP applications.
+Langtune is intended for building and fine-tuning large language models with LoRA. It can be used for text classification, summarization, question answering, and other NLP tasks.
 
 ---
 
 ## Getting Started
 
-Install with pip:
+Install:
 
 ```bash
 pip install langtune
 ```
 
-Minimal example:
+Example usage:
 
 ```python
 import torch
@@ -104,28 +103,28 @@ with torch.no_grad():
     print('Output shape:', out.shape)
 ```
 
-For more details, see the [Documentation](docs/index.md) and `src/langtune/cli/finetune.py`.
+See the [Documentation](docs/index.md) and `src/langtune/cli/finetune.py` for more details.
 
 ---
 
 ## Supported Python Versions
-- Python 3.8+
+- Python 3.8 or newer
 
 ---
 
 ## Why langtune?
 
-- Parameter-efficient fine-tuning with LoRA adapters
-- Modular transformer backbone for flexible model design
-- Unified interface for open-source language models
-- Designed for both research and production
-- Efficient memory usage for large models
+- Fine-tuning with LoRA adapters
+- Modular transformer design
+- Unified interface for language models
+- Suitable for research and production
+- Efficient memory usage
 
 ---
 
 ## Architecture Overview
 
-Langtune uses a modular transformer backbone with LoRA adapters in attention and MLP layers. This allows adaptation of pre-trained models with fewer trainable parameters.
+Langtune uses a transformer backbone with LoRA adapters in attention and MLP layers. This enables adaptation of pre-trained models with fewer trainable parameters.
 
 ### Model Data Flow
 
@@ -296,12 +295,14 @@ model.finetune(dataset, config_path="configs/custom_config.yaml")
 - For advanced usage, see `src/langtune/cli/finetune.py`.
 
 ## Contributing
-We welcome contributions. See the [Contributing Guide](CONTRIBUTING.md) for details.
+Contributions are welcome. See the [Contributing Guide](CONTRIBUTING.md) for details.
 
-## License & Citation
+## License
 
 This project is licensed under the MIT License. See [LICENSE](LICENSE) for details.
 
+## Citation
+
 If you use langtune in your research, please cite:
 
 ```bibtex

{langtune-0.0.2 → langtune-0.0.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "langtune"
-version = "0.0.2"
+version = "0.0.3"
 description = "A package for finetuning text models."
 authors = [
     { name = "Pritesh Raj", email = "priteshraj41@gmail.com" }

{langtune-0.0.2 → langtune-0.0.3/src/langtune.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: langtune
-Version: 0.0.2
+Version: 0.0.3
 Summary: A package for finetuning text models.
 Author-email: Pritesh Raj <priteshraj41@gmail.com>
 License: MIT License
@@ -39,7 +39,7 @@ Requires-Dist: pyyaml
 Requires-Dist: scipy
 Dynamic: license-file
 
-# Langtune: Large Language Models (LLMs) with Efficient LoRA Fine-Tuning for Text
+# Langtune: Efficient LoRA Fine-Tuning for Text LLMs
 
 <hr/>
 <p align="center">
@@ -60,8 +60,8 @@ Dynamic: license-file
 </p>
 
 <p align="center">
-  <b>Langtune provides modular components for text models and LoRA-based fine-tuning.</b><br/>
-  <span style="font-size:1.1em"><i>Adapt and fine-tune language models for a range of NLP tasks.</i></span>
+  <b>Langtune is a Python package for fine-tuning large language models on text data using LoRA.</b><br/>
+  <span style="font-size:1.1em"><i>Provides modular components for adapting language models to various NLP tasks.</i></span>
 </p>
 <hr/>
 
@@ -89,41 +89,40 @@ Dynamic: license-file
 - [Examples & Use Cases](#examples--use-cases)
 - [Extending the Framework](#extending-the-framework)
 - [Contributing](#contributing)
-- [FAQ](#faq)
+- [License](#license)
 - [Citation](#citation)
 - [Acknowledgements](#acknowledgements)
-- [License](#license)
 
 ---
 
 ## Features
-- LoRA adapters for parameter-efficient fine-tuning of LLMs
+- LoRA adapters for efficient fine-tuning
 - Modular transformer backbone
-- Model zoo for open-source language models
+- Model zoo for language models
 - Configurable and extensible codebase
-- Checkpointing and resume support
+- Checkpointing and resume
 - Mixed precision and distributed training
-- Built-in metrics and visualization tools
-- CLI for fine-tuning and evaluation
-- Extensible callbacks (early stopping, logging, etc.)
+- Metrics and visualization tools
+- CLI for training and evaluation
+- Callback support (early stopping, logging, etc.)
 
 ---
 
 ## Showcase
 
-Langtune is a framework for building and fine-tuning large language models with LoRA support. It is suitable for tasks such as text classification, summarization, question answering, and other NLP applications.
+Langtune is intended for building and fine-tuning large language models with LoRA. It can be used for text classification, summarization, question answering, and other NLP tasks.
 
 ---
 
 ## Getting Started
 
-Install with pip:
+Install:
 
 ```bash
 pip install langtune
 ```
 
-Minimal example:
+Example usage:
 
 ```python
 import torch
@@ -145,28 +144,28 @@ with torch.no_grad():
     print('Output shape:', out.shape)
 ```
 
-For more details, see the [Documentation](docs/index.md) and `src/langtune/cli/finetune.py`.
+See the [Documentation](docs/index.md) and `src/langtune/cli/finetune.py` for more details.
 
 ---
 
 ## Supported Python Versions
-- Python 3.8+
+- Python 3.8 or newer
 
 ---
 
 ## Why langtune?
 
-- Parameter-efficient fine-tuning with LoRA adapters
-- Modular transformer backbone for flexible model design
-- Unified interface for open-source language models
-- Designed for both research and production
-- Efficient memory usage for large models
+- Fine-tuning with LoRA adapters
+- Modular transformer design
+- Unified interface for language models
+- Suitable for research and production
+- Efficient memory usage
 
 ---
 
 ## Architecture Overview
 
-Langtune uses a modular transformer backbone with LoRA adapters in attention and MLP layers. This allows adaptation of pre-trained models with fewer trainable parameters.
+Langtune uses a transformer backbone with LoRA adapters in attention and MLP layers. This enables adaptation of pre-trained models with fewer trainable parameters.
 
 ### Model Data Flow
 
@@ -337,12 +336,14 @@ model.finetune(dataset, config_path="configs/custom_config.yaml")
 - For advanced usage, see `src/langtune/cli/finetune.py`.
 
 ## Contributing
-We welcome contributions. See the [Contributing Guide](CONTRIBUTING.md) for details.
+Contributions are welcome. See the [Contributing Guide](CONTRIBUTING.md) for details.
 
-## License & Citation
+## License
 
 This project is licensed under the MIT License. See [LICENSE](LICENSE) for details.
 
+## Citation
+
 If you use langtune in your research, please cite:
 
 ```bibtex