Instructions to use OccultAI/Ouroboros-24B-v1.4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OccultAI/Ouroboros-24B-v1.4 with Transformers:

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

pipe = pipeline("text-generation", model="OccultAI/Ouroboros-24B-v1.4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OccultAI/Ouroboros-24B-v1.4")
model = AutoModelForCausalLM.from_pretrained("OccultAI/Ouroboros-24B-v1.4", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OccultAI/Ouroboros-24B-v1.4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OccultAI/Ouroboros-24B-v1.4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OccultAI/Ouroboros-24B-v1.4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OccultAI/Ouroboros-24B-v1.4

SGLang

How to use OccultAI/Ouroboros-24B-v1.4 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 "OccultAI/Ouroboros-24B-v1.4" \
    --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": "OccultAI/Ouroboros-24B-v1.4",
		"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 "OccultAI/Ouroboros-24B-v1.4" \
        --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": "OccultAI/Ouroboros-24B-v1.4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OccultAI/Ouroboros-24B-v1.4 with Docker Model Runner:
```
docker model run hf.co/OccultAI/Ouroboros-24B-v1.4
```
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.

🐍 Ouroboros 24B v1.4

architecture: MistralForCausalLM
models:
  - model: B:\24B\Goetia-24B-v1.4
merge_method: ouroboros_doppelganger
parameters:
  num_phantoms: 8        # K synthetic spectral variations generated per tensor
  variance: 0.05         # spectral perturbation strength (SCE-inspired "variance")
  rank_decay: 2.0        # decays perturbation budget for lower singular values
  density: 0.5           # DELLA-style row-wise keep density for phantom deltas
  epsilon: 0.15          # DELLA-style keep-probability half-width
  select_topk: 0.5       # SCE-style cross-phantom variance selection fraction
  saliency_gate: true    # Arcee-Fusion-style KL/diff saliency gating
  fusion_mode: cosine    # "cosine" (Model Stock consensus) or "karcher" (Riemannian mean)
  blend_ratio: 0.3       # how much of the simulated ensemble to fold back in
  max_iter: 100          # Karcher mean iterations (only used if fusion_mode: karcher)
  tol: 1.0e-9            # Karcher mean convergence tolerance
  seed: 420 # null       # set an int for reproducible phantom generation
dtype: float32
out_dtype: bfloat16
tokenizer:
  source: union
chat_template: auto
name: 🐍 Ouroboros Doppelganger 24B

Downloads last month: 159

Safetensors

Model size

24B params

Tensor type

BF16

Model tree for OccultAI/Ouroboros-24B-v1.4

Base model

Naphula/Goetia-24B-v1.4

Finetuned

(2)

this model

Quantizations

2 models