darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic

Instructions to use CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic with Transformers:

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

pipe = pipeline("image-text-to-text", model="CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-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("CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic")
model = AutoModelForMultimodalLM.from_pretrained("CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-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 CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-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": "CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-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/CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic

SGLang

How to use CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-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 "CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-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": "CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-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 "CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-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": "CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-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"
						}
					}
				]
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic with Docker Model Runner:
```
docker model run hf.co/CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic
```

This is a decensored version of TeichAI/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2, made using Heretic v1.3.0

This model is reproducible!

See the README in the reproduce directory for more information.

Abliteration parameters

Parameter	Value
direction_index	41.77
attn.o_proj.max_weight	1.22
attn.o_proj.max_weight_position	51.32
attn.o_proj.min_weight	1.21
attn.o_proj.min_weight_distance	32.79
mlp.down_proj.max_weight	1.44
mlp.down_proj.max_weight_position	42.02
mlp.down_proj.min_weight	0.13
mlp.down_proj.min_weight_distance	37.15

Performance

Metric	This model	Original model (TeichAI/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2)
KL divergence	0.0774	0 (by definition)
Refusals	8/100	98/100

Qwen3.6 27B x Claude Opus 4.x - v2

Benchmarks

Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2
         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.665,0.831,0.910,0.790,0.456,0.813,0.772

Qwen3.6-27B
         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.647,0.803,0.910,0.773,0.450,0.806,0.742

Provided by @nightmedia. All benchmarks were done in mxfp8 precision

🧬 Datasets:

⚡ Use cases

Coding
Creative Writing
Visual Understanding
General Purpose

Citations and Contributions

@unsloth - This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.
@Qwen - Providing a fantastic, native-multimodal base model

Usage

If you need help setting up and configuring this model please follow the Qwen team's instructions in the original model's README

Downloads last month: 3

Safetensors

Model size

27B params

Tensor type

BF16

Model tree for CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic

Base model

Qwen/Qwen3.6-27B

Finetuned

(399)

this model

Datasets used to train CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic

Collection including CCSSNE/darkc0de-Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic

Qwopus3.6

Collection

3 items • Updated Jul 3