Instructions to use Naphula/Cyberdonia-24B-v8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Naphula/Cyberdonia-24B-v8 with Transformers:

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

pipe = pipeline("text-generation", model="Naphula/Cyberdonia-24B-v8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Naphula/Cyberdonia-24B-v8")
model = AutoModelForCausalLM.from_pretrained("Naphula/Cyberdonia-24B-v8", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Naphula/Cyberdonia-24B-v8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Naphula/Cyberdonia-24B-v8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Naphula/Cyberdonia-24B-v8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Naphula/Cyberdonia-24B-v8

SGLang

How to use Naphula/Cyberdonia-24B-v8 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 "Naphula/Cyberdonia-24B-v8" \
    --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": "Naphula/Cyberdonia-24B-v8",
		"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 "Naphula/Cyberdonia-24B-v8" \
        --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": "Naphula/Cyberdonia-24B-v8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Naphula/Cyberdonia-24B-v8 with Docker Model Runner:
```
docker model run hf.co/Naphula/Cyberdonia-24B-v8
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

⚠️ Warning: This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use Mistral Tekken chat template.

🚀 Cyberdonia 24B v8

⚗️ The Alchemical Crucible 🔥

This is a merge of pre-trained language models created using mergekit-exp, a custom fork of the official mergekit. This model was merged using the della merge method.

The model is fully uncensored with 0 refusals despite not using any form of Heretic/ablation due to the un-normalized magnitude of the merge.

In my opinion this model produces superior writing to Cydonia-24B-v4.3-absolute-heresy. Several other variants were tested including swapping v4q in place of v4y, yet this produced inferior results.

Audit

v8
[DELLA Audit] Layer: model.layers.0.mlp.up_proj.weight | Lambda=1.00
  [BASE] !models--anthracite-core--Mistral-Small-3.2-24B-In
  !models--TheDrummer--Cydonia-24B-v4.3             : ███████████████████                                 39.5% (W:0.40 D:0.90 N:0.92 E:0.09)
  Cydonia-24B-v4x-Q8_0                              : ████████████████████                                40.2% (W:0.80 D:0.90 N:0.47 E:0.09)
  Cydonia-24B-v4y-Q8_0                              : ██████████                                          20.3% (W:0.40 D:0.90 N:0.47 E:0.09)

v12
[DELLA Audit] Layer: model.layers.0.mlp.up_proj.weight | Lambda=1.00
  [BASE] !models--anthracite-core--Mistral-Small-3.2-24B-In
  !models--TheDrummer--Cydonia-24B-v4.3             : ████████                                            17.5% (W:0.40 D:0.90 N:0.92 E:0.09)
  Cydonia-24B-v4q-Q8_0                              : ████████████████████████████████                    64.7% (W:0.40 D:0.90 N:3.41 E:0.09)
  Cydonia-24B-v4x-Q8_0                              : ████████                                            17.8% (W:0.80 D:0.90 N:0.27 E:0.09)

The following models were included in this merge:

🙏 Thanks @mradermacher and other quantizers.

💾 GGUFs:
- mradermacher/Cyberdonia-24B-v8-GGUF
- mradermacher/Cyberdonia-24B-v8-i1-GGUF

⚙️ See this page for recommended settings.

🧙 Invocation Grimoires 🐙

🌋 Hellforged Parameters

mergekit_config.yml

architecture: MistralForCausalLM
base_model: B:\24B\!models--anthracite-core--Mistral-Small-3.2-24B-Instruct-2506-Text-Only
models:
  - model: B:\24B\Cydonia-24B-v4x-Q8_0
    parameters:
      weight: 0.8
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\!models--TheDrummer--Cydonia-24B-v4.3
    parameters:
      weight: 0.4
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\Cydonia-24B-v4y-Q8_0
    parameters:
      weight: 0.4
      density: 0.9
      epsilon: 0.09
merge_method: della
parameters:
  lambda: 1.0
  normalize: false
  int8_mask: false
  rescale: true
dtype: float32
out_dtype: bfloat16
tokenizer:
  source: union
chat_template: auto