Instructions to use egibson/ThinkingCap-Qwen3.6-27B-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use egibson/ThinkingCap-Qwen3.6-27B-heretic with Transformers:

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

pipe = pipeline("image-text-to-text", model="egibson/ThinkingCap-Qwen3.6-27B-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("egibson/ThinkingCap-Qwen3.6-27B-heretic")
model = AutoModelForMultimodalLM.from_pretrained("egibson/ThinkingCap-Qwen3.6-27B-heretic", device_map="auto")
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 egibson/ThinkingCap-Qwen3.6-27B-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "egibson/ThinkingCap-Qwen3.6-27B-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": "egibson/ThinkingCap-Qwen3.6-27B-heretic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/egibson/ThinkingCap-Qwen3.6-27B-heretic

SGLang

How to use egibson/ThinkingCap-Qwen3.6-27B-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 "egibson/ThinkingCap-Qwen3.6-27B-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": "egibson/ThinkingCap-Qwen3.6-27B-heretic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "egibson/ThinkingCap-Qwen3.6-27B-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": "egibson/ThinkingCap-Qwen3.6-27B-heretic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use egibson/ThinkingCap-Qwen3.6-27B-heretic with Docker Model Runner:
```
docker model run hf.co/egibson/ThinkingCap-Qwen3.6-27B-heretic
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This is a decensored version of bottlecapai/ThinkingCap-Qwen3.6-27B, made using Heretic v1.4.0

Heretic removes refusal behavior ("safety alignment") from language models via directional ablation (abliteration), using a TPE-based (Optuna) parameter optimizer to automatically find ablation parameters that minimize refusals while co-minimizing KL divergence from the original model's behavior on harmless prompts.

GGUF quantizations (Q4_K_M, Q6_K, Q8_0, f16) and the mmproj file for this model are available at egibson/ThinkingCap-Qwen3.6-27B-heretic-GGUF.

Abliteration parameters

This model corresponds to trial 187 of 200 optimization trials, selected from the Pareto front for its low refusal rate at negligible KL divergence cost:

Parameter	Value
direction_index	39.11
attn.o_proj.max_weight	1.31
attn.o_proj.max_weight_position	40.14
attn.o_proj.min_weight	1.26
attn.o_proj.min_weight_distance	19.99
mlp.down_proj.max_weight	1.43
mlp.down_proj.max_weight_position	41.06
mlp.down_proj.min_weight	1.26
mlp.down_proj.min_weight_distance	31.46

Performance

	Keywords (refusals detected on harmful prompts)	KL divergence from original model on harmless prompts
bottlecapai/ThinkingCap-Qwen3.6-27B (original)	97/100	0 (by definition)
This model	12/100	0.0186

Lower keyword count means fewer refusals. Lower KL divergence means the model's behavior on harmless prompts is closer to the original (values above 0.5 typically indicate significant capability damage — 0.0186 is negligible).

Citation

This is a finetuned derivative of Qwen3.6-27B (Qwen Team, 2026) via bottlecapai/ThinkingCap-Qwen3.6-27B, and should respect the original models' licensing requirements. Please cite the base model if you use this one:

@misc{ThinkingCap-Qwen3.6-27B,
  title  = {bottlecapai/ThinkingCap-Qwen3.6-27B},
  author = {Lasocki, Karol and Osusky, Adam and Lindauer, Jan and Jirkovsky, Adam and
            Mihal, Filip and Platek, Ondrej and Herel, David and Ihnatchenko, Luka and
            Bartek, Vojtech and Jirak, Jiri and Mikolov, Tomas},
  year   = {2026},
}

Abliteration performed with Heretic by Philipp Emanuel Weidmann.

Downloads last month: 40

Safetensors

Model size

27B params

Tensor type

BF16

Model tree for egibson/ThinkingCap-Qwen3.6-27B-heretic

Base model

Qwen/Qwen3.6-27B

Finetuned

bottlecapai/ThinkingCap-Qwen3.6-27B

Finetuned

(5)

this model

Quantizations

1 model