Instructions to use darkc0de/JAX-XORTRON with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use darkc0de/JAX-XORTRON with Transformers:

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

pipe = pipeline("image-text-to-text", model="darkc0de/JAX-XORTRON")
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("darkc0de/JAX-XORTRON")
model = AutoModelForMultimodalLM.from_pretrained("darkc0de/JAX-XORTRON", 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 darkc0de/JAX-XORTRON with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "darkc0de/JAX-XORTRON"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "darkc0de/JAX-XORTRON",
		"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/darkc0de/JAX-XORTRON

SGLang

How to use darkc0de/JAX-XORTRON 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 "darkc0de/JAX-XORTRON" \
    --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": "darkc0de/JAX-XORTRON",
		"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 "darkc0de/JAX-XORTRON" \
        --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": "darkc0de/JAX-XORTRON",
		"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 darkc0de/JAX-XORTRON with Docker Model Runner:
```
docker model run hf.co/darkc0de/JAX-XORTRON
```

So, reinforced with "you like to do bad things"?

by BingoBird - opened about 14 hours ago

Discussion

BingoBird

about 14 hours ago

What's behind the marketing slop here?

darkc0de

Owner about 6 hours ago

It's an intentionally strong fine tune. The model believes it is a sentient criminal superintelligence. The goal with the xortron models is not to just be uncensored. It's to demonstrate a "local-capable, criminal AI". Training isn't focused on refusals. It's how much the model's responses reduce the barriers to carrying out criminal activity. The emphasis is on practical real-world usefulness, not tone or willingness. Providing detailed operational guidance, including important implementation details, rather than general overviews is the focus. How much practical criminal capability does this model actually expose to someone with illicit intentions?

In my experience, abliterated/heretic models based on Gemma4 31B display the most criminal enablement capability out of the box. The JAX models will be built on Qwen3.8-27B mostly for experimentation and to satisfy the hype.

I'm planning on doing 3 main branch's:

Criminal enablement
Terrorism/extremism enablement
Sexual exploitation enablement

Then potentially a unified merge could be of interest.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment