Project Vision/Roadmap

The amount of interest in this project has far surpassed my expectations, and there have been many interesting suggestions from the community regarding what features could be added in the future. In the past weeks, I have thought about the direction I want the project to take, and am now trying to write down the conclusions I arrived at.

The Vision

• Heretic will be a universal tool for training-free modification of language models.
• By default, it will perform censorship removal, as it does now.
• It will include relevant research features to facilitate the understanding of model internals, and the development of new intervention techniques.

Roadmap

Heretic 1.2.0

• Quantization + LoRA support (#60)
• Injection of prefixes and suffixes into prompts (@p-e-w)
• Separate system prompts for good/bad prompts (@p-e-w)
• Experiment with using Heretic for slop removal (@p-e-w)
• Support for multimodal models (#18)

Future versions

• Support for hybrid models (#43)
• Configurable response prefixes (@p-e-w)
• Basic plugin system with support for scorers (#25, #53)
• Modifier plugins for different abliteration techniques
• Logger plugins (file/WandB)
• Fix broken models:
  • #27
  • #61
  • #62
  • #64
  • #82
  • #84
  • #90
• Stackable configuration files

---

Feedback and feature suggestions are welcome!