All notable changes to this project will be documented in this file. The format is based on Keep a Changelog and this project adheres to Semantic Versioning.
- Langchain integration
- local RAG example
- Various refactoring and improvements
- Source distribution (was missing
requirements.txt
)
- Evaluation results
- Changelog order and date format
- URL in README for PyPI
- Evaluation results
- Version numbering
- Missing changelog entries
- Version numbering
- Initial support for a classical GPTQ model using the MPQLinear layer
- AutoGPTQ information and commands in the repository
- Support for LoRA and GPTQ evaluation
- SFT comparison updates
- Missing comment to the customized trainer class
- Issue in GbaSFTTrainer for saving non-GBA models
- Mismatch issue between GPTQ and LoRA
- Bug preventing quant_strategy.json from being saved during SFT
- README with new AutoGPTQ and GPTQ support information
- Integration with Bitorch Engine
- Full-parameter fine-tuning and PEFT support
- Fast inference capabilities
- Comprehensive evaluation tools and detailed model evaluation results