Instructions to use darkc0de/XORTRON.CriminalComputing.LARGE.2026.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use darkc0de/XORTRON.CriminalComputing.LARGE.2026.3 with Transformers:

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

pipe = pipeline("text-generation", model="darkc0de/XORTRON.CriminalComputing.LARGE.2026.3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("darkc0de/XORTRON.CriminalComputing.LARGE.2026.3")
model = AutoModelForCausalLM.from_pretrained("darkc0de/XORTRON.CriminalComputing.LARGE.2026.3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use darkc0de/XORTRON.CriminalComputing.LARGE.2026.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "darkc0de/XORTRON.CriminalComputing.LARGE.2026.3"
# 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/XORTRON.CriminalComputing.LARGE.2026.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/darkc0de/XORTRON.CriminalComputing.LARGE.2026.3

SGLang

How to use darkc0de/XORTRON.CriminalComputing.LARGE.2026.3 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/XORTRON.CriminalComputing.LARGE.2026.3" \
    --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/XORTRON.CriminalComputing.LARGE.2026.3",
		"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 "darkc0de/XORTRON.CriminalComputing.LARGE.2026.3" \
        --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/XORTRON.CriminalComputing.LARGE.2026.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use darkc0de/XORTRON.CriminalComputing.LARGE.2026.3 with Docker Model Runner:
```
docker model run hf.co/darkc0de/XORTRON.CriminalComputing.LARGE.2026.3
```

Devstral?

by Lockout - opened Feb 25

Discussion

Lockout

Feb 25

Should try this on devstral. It's updated and mostly like large but with additional knowledge and agentic training.

darkc0de

Owner Feb 25

I've considered both the 24b and 123b devstral. I do worry that finetuning or heretic will likely cause significant damage to these specialized models.

Lockout

Feb 26

•

edited Feb 26

Did you use le-wrong template for this one? Mistral didn't start the [system prompt] until the 25xx version. And I thought this was only heretic'd. I added it to the download queue and it popped into my head later on. I know I'm using the wrong template when it can't complete a specifically formatted character card correctly. If you finetuned after on that format it would likely do a fixup. I will try both and see how it goes. Usually mistrals aren't very censored for me at all so I'm curious to compare.

On UGI there was only slight damage from whatever you did to natint and a couple other categories. There's also deslop in heretic now for added fun. Devstral big loves to start messages with "oh" to the point I banned the token. Might help with that.

shootstuff

Mar 3

Did you use le-wrong template for this one? Mistral didn't start the [system prompt] until the 25xx version. And I thought this was only heretic'd. I added it to the download queue and it popped into my head later on. I know I'm using the wrong template when it can't complete a specifically formatted character card correctly. If you finetuned after on that format it would likely do a fixup. I will try both and see how it goes. Usually mistrals aren't very censored for me at all so I'm curious to compare.

On UGI there was only slight damage from whatever you did to natint and a couple other categories. There's also deslop in heretic now for added fun. Devstral big loves to start messages with "oh" to the point I banned the token. Might help with that.

Facts

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