My mergedhereticFT model, abliterated using p-e-w's Heretic tool, and fine tuned on my thebigdataset dataset. I don't know how much the fine tuning/healing helped but it's still coherent, so I'm calling it a success. Uploaded to track my progress.
Uploaded finetuned model
- Developed by: DrRiceIO7
- License: apache-2.0
- Finetuned from model : DrRiceIO7/heretic-checkpoint
This gemma3 model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 315