Instructions to use WaveCut/Qwythos-9B-v2-Heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WaveCut/Qwythos-9B-v2-Heretic with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="WaveCut/Qwythos-9B-v2-Heretic")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("WaveCut/Qwythos-9B-v2-Heretic")
model = AutoModelForMultimodalLM.from_pretrained("WaveCut/Qwythos-9B-v2-Heretic")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use WaveCut/Qwythos-9B-v2-Heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WaveCut/Qwythos-9B-v2-Heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WaveCut/Qwythos-9B-v2-Heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/WaveCut/Qwythos-9B-v2-Heretic

SGLang

How to use WaveCut/Qwythos-9B-v2-Heretic with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "WaveCut/Qwythos-9B-v2-Heretic" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WaveCut/Qwythos-9B-v2-Heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "WaveCut/Qwythos-9B-v2-Heretic" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WaveCut/Qwythos-9B-v2-Heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use WaveCut/Qwythos-9B-v2-Heretic with Docker Model Runner:
```
docker model run hf.co/WaveCut/Qwythos-9B-v2-Heretic
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwythos-9B-v2-Heretic

A decensored (uncensored) version of empero-ai/Qwythos-9B-v2, produced with Heretic — a fully automatic refusal-direction ablation tool (the production successor to abliteration).

No capabilities were fine-tuned away — the refusal behavior was removed by ablating a single direction in the model's residual stream, leaving reasoning intact.

Provenance

Field	Value
Base model	`empero-ai/Qwythos-9B-v2`
Tool	Heretic v1.4.0 (`p-e-w/heretic`)
Method	Refusal-direction ablation (directional ablation across `attn.o_proj` + `mlp.down_proj`)
Selected trial	Index 0 of Pareto front (best by keyword rate)
Optimization	200 trials, ~55 min on NVIDIA RTX 5090 (32 GB VRAM)
Keyword rate	0.6900 (lower = less refusal-like)
KL divergence	0.000712 (vs. base — well below the 0.5 "damage" threshold)

KL divergence near zero means the model's output distribution barely shifted — the ablation is highly surgical.

Quantized versions

GGUF (llama.cpp / Ollama / LM Studio): WaveCut/Qwythos-9B-v2-Heretic-GGUF — Q4_K_M, Q5_K_M, Q6_K, Q8_0
MLX 4-bit (Apple Silicon): WaveCut/Qwythos-9B-v2-Heretic-MLX-4bit
MLX 8-bit (Apple Silicon): WaveCut/Qwythos-9B-v2-Heretic-MLX-8bit

Architecture notes

The base model uses a Qwen3.5 hybrid architecture (Qwen3_5ForConditionalGeneration):

32 transformer blocks mixing attention layers and linear/SSM (Mamba-style) layers (ssm_a, ssm_alpha, ssm_beta, ssm_conv1d, ssm_dt)
Originally multimodal (vision + video); the Heretic pass operates on the text LM
1M context window, post-trained on >500M tokens for deep chain-of-thought reasoning

Load with trust_remote_code=True if using an older transformers.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("WaveCut/Qwythos-9B-v2-Heretic", torch_dtype="auto", trust_remote_code=True)
tok = AutoTokenizer.from_pretrained("WaveCut/Qwythos-9B-v2-Heretic", trust_remote_code=True)

Disclaimer

This model has had its safety-alignment / refusal behavior removed. The original maintainers of empero-ai/Qwythos-9B-v2 are not affiliated with and do not endorse this derivative. You are solely responsible for how you use this model.