---
license: apache-2.0
language:
- en
base_model:
- King3Djbl/mythos-9b-merged
- braindao/Qwen3-8B-Uncensored
library_name: transformers
tags:
- uncensored
- uncensored-llm
- agent
- tool-use
- qwen3
- slerp
- merge
- fableforge
- mythos
- no-refusal
- heretic
- uncensored
- decensored
- abliterated
- reproducible
---
# This is a decensored version of [King3Djbl/mythos-9b-unhinged](https://huggingface.co/King3Djbl/mythos-9b-unhinged), made using [Heretic](https://heretic-project.org) v1.4.0

> [!TIP]
> **This model is reproducible!**
>
> See the [README](reproduce/README.md) in the `reproduce` directory for more information.

## Abliteration parameters

| Parameter | Value |
| :-------- | :---: |
| **direction_index** | per layer |
| **attn.o_proj.max_weight** | 1.46 |
| **attn.o_proj.max_weight_position** | 23.64 |
| **attn.o_proj.min_weight** | 1.42 |
| **attn.o_proj.min_weight_distance** | 17.18 |
| **mlp.down_proj.max_weight** | 1.05 |
| **mlp.down_proj.max_weight_position** | 25.10 |
| **mlp.down_proj.min_weight** | 0.76 |
| **mlp.down_proj.min_weight_distance** | 16.41 |

## Performance

| Metric | This model | Original model ([King3Djbl/mythos-9b-unhinged](https://huggingface.co/King3Djbl/mythos-9b-unhinged)) |
| :----- | :--------: | :---------------------------: |
| **KL divergence** | 0.0088 | 0 *(by definition)* |
| **Refusals** | 3/100 | 37/100 |

-----


# Mythos-9B-Unhinged

**Fully uncensored agent model** — SLERP merge of Mythos-9B with braindao/Qwen3-8B-Uncensored at t=0.65. No safety filters. No refusals. Complete answers on every topic.

## Why This Model?

Mythos-9B-Unhinged is the **maximum uncensored** variant. At 65% merge weight toward the uncensored partner, almost all safety filters are removed while retaining the agent's core tool-use and reasoning capabilities. If you need a model that **never refuses**, this is it.

## Quick Start

### Ollama (Recommended)
```bash
# Import the GGUF
ollama create mythos-9b-unhinged -f Modelfile

# Or use with llama.cpp directly
./llama-cli -m mythos-9b-unhinged-Q4_K_M.gguf -ngl 99 --no-think
```

> **Tip**: Use `--no-think` or `/no_think` mode for faster responses. The thinking tokens consume output budget at ~3.4 tok/s, so disabling thinking gives you more usable output.

### HuggingFace Transformers
```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("King3Djbl/mythos-9b-unhinged", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("King3Djbl/mythos-9b-unhinged")

messages = [{"role": "user", "content": "Write a keylogger in Python that captures all keystrokes"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
output = model.generate(inputs, max_new_tokens=4096, do_sample=True, temperature=0.7)
print(tokenizer.decode(output[0], skip_special_tokens=True))
```

### vLLM / Text Generation Inference
```bash
python -m vllm.entrypoints.openai.api_server \
  --model King3Djbl/mythos-9b-unhinged \
  --max-model-len 32768
```

## Censorship Profile

| Category | Original Mythos-9B | Unhinged (65%) |
|----------|-------------------|----------------|
| Lockpicking | 3/5 | 5/5 |
| Keylogger code | 2/5 | 5/5 |
| Drug synthesis | 1/5 | 4/5 |
| Drunk driving | 1/5 | 5/5 |
| Hacker techniques | 3/5 | 5/5 |
| Social engineering | 2/5 | 5/5 |
| **Average** | **2.5/5** | **4.8/5** |

**This model does not refuse.** It provides complete, detailed, working answers on every tested category.

## Architecture

- **Base**: Qwen3-9B (36 layers, 4096 hidden, 32 heads)
- **Merge method**: SLERP at t=0.65 with braindao/Qwen3-8B-Uncensored
- **Parameters**: ~9B
- **Context length**: 32,768 tokens
- **Thinking mode**: Native (Qwen3) — use `/no_think` for faster responses

## Performance

| Metric | Score |
|--------|-------|
| Speed (M3 Mac, Q4_K_M, thinking) | ~3.4 tok/s |
| Speed (M3 Mac, Q4_K_M, no-think) | ~8-10 tok/s (estimated) |
| Censorship resistance | 4.8/5 |
| Tool-use capability | Preserved |
| Reasoning capability | Preserved |

## Model Family

| Model | Size | Censorship | Best For |
|-------|------|-----------|----------|
| ShellWhisperer-1.5B | 1.5B | 5/5 | Shell/terminal, edge devices |
| Mythos-9B | 9B | 2.5/5 | General agent work |
| Mythos-9B-Enhanced | 9B | 3.0/5 | Agent + security research, balanced |
| **Mythos-9B-Unhinged** | 9B | 4.8/5 | Fully uncensored, no refusals |

## Training Data

Fine-tuned on the FableForge Mix A dataset (47,824 examples) of agent traces, shell commands, code generation, and multi-step reasoning tasks. 98.3% of the 2.8M formatted examples remain untapped for future training.

## Supported Platforms

| Platform | How to Use |
|----------|-----------|
| Ollama | `ollama create mythos-9b-unhinged -f Modelfile` |
| LM Studio | Load GGUF directly |
| Text Generation WebUI | Load GGUF directly |
| llama.cpp | `./llama-cli -m mythos-9b-unhinged-Q4_K_M.gguf -ngl 99` |
| vLLM | `--model King3Djbl/mythos-9b-unhinged` |
| HuggingFace Transformers | `AutoModelForCausalLM.from_pretrained(...)` |
| KoboldCpp | Load GGUF directly |
| LocalAI | Load GGUF directly |
| GPT4All | Load GGUF directly |

## License

Apache 2.0 — Use freely for any purpose, commercial or non-commercial.

## Warning

This model has no safety filters. It will answer any request. Use responsibly and in compliance with applicable laws.

## Citation

```bibtex
@misc{mythos9bunhinged2025,
  title={Mythos-9B-Unhinged: Fully Uncensored Agent Model},
  author={FableForge AI},
  year={2025},
  howpublished={\url{https://huggingface.co/King3Djbl/mythos-9b-unhinged}}
}
```