Starstruk Logo MarkStarstruk

v1.2.0

games-on-whales/wolfv1.2.0Feb 14, 2026by p-e-w

AI Summary

This release focuses on enhancing optimization workflows with a new LoRA-based abliteration engine, GPU enumeration, and progress saving capabilities. It also includes bug fixes, code refactoring, and new configuration options to improve stability and resource management.

Key Highlights

  • New LoRA-based abliteration engine with support for 4-bit quantization.
  • Added GPU enumeration on startup and a `max_memory` setting for resource management.
  • Implemented saving and resuming optimization progress.
  • Broad support for Vision-Language (VL) models.

New Features

  • LoRA-based abliteration engine with support for 4-bit quantization
  • Enumeration of all available GPUs on startup
  • Ability to run more trials after optimization is complete
  • Saving and resuming optimization progress
  • Broad support for VL models
  • max_memory setting to limit memory usage
  • Mechanism to avoid excessive low-divergence iteration
  • Magnitude-Preserving Orthogonal Ablation implementation
  • Prompt modification functionality
  • Example config file for slop reduction

Full Release Notes

## Changes
* @noctrex added a `max_memory` setting to limit memory usage in https://github.com/p-e-w/heretic/pull/83
* @spikymoth added a mechanism to avoid excessive low-divergence iteration in https://github.com/p-e-w/heretic/pull/73
* @accemlcc implemented a new LoRA-based abliteration engine with support for 4-bit quantization in https://github.com/p-e-w/heretic/pull/60
* @accemlcc added enumeration of all available GPUs on startup in https://github.com/p-e-w/heretic/pull/86
* @Vinayyyy7 added the ability to run more trials after optimization is complete in https://github.com/p-e-w/heretic/pull/76
* @anrp fixed MXFP4 loading in https://github.com/p-e-w/heretic/pull/107
* @anrp refactored the save machinery in https://github.com/p-e-w/heretic/pull/110
* @anrp added broad support for VL models in https://github.com/p-e-w/heretic/pull/108
* @anrp implemented saving and resuming optimization progress in https://github.com/p-e-w/heretic/pull/106, https://github.com/p-e-w/heretic/pull/119, and https://github.com/p-e-w/heretic/pull/116
* @spikymoth implemented Magnitude-Preserving Orthogonal Ablation in https://github.com/p-e-w/heretic/pull/52
* @salmanmkc upgraded GitHub Actions to the latest versions in https://github.com/p-e-w/heretic/pull/136 and https://github.com/p-e-w/heretic/pull/137
* @p-e-w added full type checking of the codebase, debug output, prompt modification functionality, and an example config file for slop reduction, and fixed various minor issues

## New Contributors
* @noctrex made their first contribution in https://github.com/p-e-w/heretic/pull/83
* @accemlcc made their first contribution in https://github.com/p-e-w/heretic/pull/60
* @anrp made their first contribution in https://github.com/p-e-w/heretic/pull/107
* @salmanmkc made their first contribution in https://github.com/p-e-w/heretic/pull/136

**Full Changelog**: https://github.com/p-e-w/heretic/compare/v1.1.0...v1.2.0