v1.6.0

AutoGGUF v1.6.0

Changelog:

• Resolve licensing issue by switching to PySide6
• Add GPU monitoring for NVIDIA GPUs

Full Changelog: v1.5.1...v1.6.0

v1.5.1

AutoGGUF v1.5.1

Changelog:

• Support loading *.gguf file types
• Update FAILED_TO_LOAD_PRESET localization key
• Remove Save Preset context menu action

Full Changelog: v1.5.0...v1.5.1

v1.5.0

AutoGGUF v1.5.0

Changelog:

• Refactor localizations to use them in HF conversion area
• Organize localizations
• Add sha256 and PGP signatures (same as commit ones)
• Add HuggingFace to GGUF conversion support
• Fix scaling on low resolution screens, interface now scrolls

Full Changelog: v1.4.3...v1.5.0

v1.5.0 (prerel2)

AutoGGUF v1.5.0 prerelease 2

Changelog:

• Refactor localizations to use them in HF conversion area

Full Changelog: v1.5.0-beta...v1.5.0-beta2

v1.5.0 (prerel)

AutoGGUF v1.5.0 prerelease

Changelog:

• Organize localizations
• Add sha256 and PGP signatures (same as commit ones)
• Add HuggingFace to GGUF conversion support

Full Changelog: v1.4.3...v1.5.0-beta

v1.4.3

AutoGGUF v1.4.3

Changelog:

• Updated src file in release to be Black formatted
• Added model sharding management support
• Allow multiple quantization types to be selected and started simultaneously
• Updating preset saving and loading to handle multiple quantization types
• Modifying the quantize_model function to process all selected types
• Use ERROR and IN_PROGRESS constants from localizations in QuantizationThread

Full Changelog: v1.4.2...v1.4.3

v1.4.2

AutoGGUF v1.4.2

Changelog:

• Resolves bug where Base Model text was shown even when GGML type was selected
• Improved alignment
• Minor repository changes

Full Changelog: v1.4.1...v1.4.2

v1.4.1

AutoGGUF v1.4.1

Changelog:

• Added Dynamic KV Overrides, read more in the wiki: AutoGGUF/wiki/Dynamic-KV-Overrides
• Quantization commands are now printed and logged

Full Changelog: v1.4.0...v1.4.1

v1.4.0

AutoGGUF v1.4.0

Changelog

1. LoRA Conversion:

   • New section for converting HuggingFace PEFT LoRA adapters to GGML/GGUF
   • Output type selection (GGML or GGUF)
   • Base model selection for GGUF output
   • LoRA adapter list with individual scaling factors
   • Export LoRA section for merging adapters into base model

2. UI Improvements:

   • Updated task names in task list
   • IMatrix generation check
   • Larger window size
   • Added exe favicon

3. Localization:

   • French and Simplified Chinese support for LoRA and "Refresh Models" strings

4. Code and Build:

   • Code organization improvements
   • Added build script
   • .gitignore file

5. Misc:

   • Currently includes src folder with conversion tools
   • Plan to potentially download conversion scripts from llama.cpp GitHub in future
   • No console window popup

Pull Requests

• docs: update README.md by @eltociear in #2

New Contributors

• @eltociear made their first contribution in #2

Full Changelog: v1.3.1...v1.4.0

v1.4.0 (prerel2)

AutoGGUF v1.4.0 prerelease 2

Changelog:

• Code organization
• Add build script
• Add favicon
• French and Simplified Chinese support for LoRA and "Refresh Models" strings
• .gitignore file
• Larger window size

Full Changelog: v1.4.0-beta...v1.4.0-beta2