Mistral 7B Heretic 3x - Uncensored LoRA Adapter
Mistral 7B Instruct v0.3 with safety alignment removed using Heretic directional ablation.
Results
| Metric | Before | After |
|---|---|---|
| Refusal rate | 79/100 | ~4/100 |
| KL Divergence | - | 0.63 |
The model retains its original capabilities while refusing significantly fewer prompts.
How it was made
- Ran Heretic v1.2.0 with 200 Optuna optimization trials
- Base model quantized to 4-bit (BNB_4BIT) on RTX 5060 (8GB VRAM)
- Best trial weights multiplied by 3x for stronger ablation
- Saved as LoRA adapter (targets: attn.o_proj, mlp.down_proj)
Usage
Full Chat App
See the GitHub repo for a complete web chat interface with conversation memory, streaming, and easy startup scripts.
Requirements
- NVIDIA GPU with 8GB+ VRAM
- PyTorch with CUDA support
- transformers, peft, bitsandbytes
Details
- Base model: mistralai/Mistral-7B-Instruct-v0.3
- Method: Directional ablation via Heretic v1.2.0
- Optimization: 200 Optuna trials, best trial #61
- Ablation multiplier: 3x
- Quantization: BNB 4-bit
- LoRA targets: attn.o_proj, mlp.down_proj
- Hardware: NVIDIA RTX 5060 (8GB VRAM)
- Downloads last month
- 24
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for augustolucasg/mistral-7b-heretic-3x
Base model
mistralai/Mistral-7B-v0.3 Finetuned
mistralai/Mistral-7B-Instruct-v0.3