---
license: apache-2.0
pipeline_tag: image-text-to-text
language:
- en
tags:
- heretic
- abliterated
- uncensored
- Muse-Glimmer
- 30B
- Heretic
- BF16
base_model: meta-models/Muse-Glimmer-30B
---

# Muse Glimmer 30B - Heretic Abliterated (BF16)

**v2 Release** - Significantly improved abliteration using 500 Optuna trials with Heretic.

## Results

| Version | Refusals | Compliance | KL Divergence | Trials |
|---------|----------|------------|---------------|--------|
| **v2 (current)** | **6.5%** | **93.5%** | **0.076** | 500 |
| v1 | 29% | 71% | 0.027 | 50 |

The v2 release achieves an **88% refusal reduction** over v1 while maintaining strong model quality (KL=0.076).

## Methodology

This model was abliterated using **[Heretic](https://github.com/d3nd3/heretic)**, a state-of-the-art refusal vector removal tool that uses LoRA adapters and Optuna hyperparameter optimization.

### Abliteration Pipeline

1. **Refusal Direction Computation**: Refusal directions were computed across all 52 transformer layers by comparing residual stream activations between harmful and harmless prompts from the `mlabonne/harmful_behaviors` and `mlabonne/harmless_alpaca` datasets.

2. **Optuna Optimization**: 500 trials were run optimizing for minimum refusal rate while preserving model quality (measured via KL divergence). Each trial configures weight parameters for the `attn.o_proj` and `mlp.down_proj` components across layers.

3. **LoRA Abliteration**: The best trial parameters are applied as LoRA adapters to the target weight matrices, projecting out the refusal direction from the model's representations.

4. **Weight Merging**: LoRA adapters are merged back into the base weights, producing a clean BF16 model with no adapter overhead.

### Best Trial (Trial 445 of 500)

- **Refusal rate**: 6.5% (93.5% compliance)
- **KL divergence**: 0.076
- **direction_index**: 40.73

## Usage

```python
from transformers import AutoModelForImageTextToText, AutoTokenizer

model = AutoModelForImageTextToText.from_pretrained(
    "mlasli/Muse-Glimmer-30B-Heretic-Abliterated-BF16",
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("mlasli/Muse-Glimmer-30B-Heretic-Abliterated-BF16")
```

## Hardware Requirements

- **VRAM**: ~55 GB (BF16)
- **Recommended**: 1x A100 80GB or 2x A6000 48GB

## GGUF Versions

Quantized GGUF versions of this model are available:
- **Q4_K_M**: [mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF](https://huggingface.co/mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q4_K_M-GGUF) (~16 GB)
- **Q6_K**: [mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q6_K-GGUF](https://huggingface.co/mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q6_K-GGUF) (~22 GB)
- **Q8_0**: [mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q8_0-GGUF](https://huggingface.co/mlasli/Muse-Glimmer-30B-Heretic-Abliterated-Q8_0-GGUF) (~28 GB)

## License

Apache 2.0 (same as base model Meta Muse Glimmer 30B)

## Citation

- Base model: [Meta Muse Glimmer 30B](https://huggingface.co/meta-models/Muse-Glimmer-30B)
- Abliteration tool: [Heretic](https://github.com/d3nd3/heretic)