Instructions to use OccultAI/Morpheus-8B-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OccultAI/Morpheus-8B-v2 with Transformers:

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

pipe = pipeline("text-generation", model="OccultAI/Morpheus-8B-v2")
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("OccultAI/Morpheus-8B-v2")
model = AutoModelForCausalLM.from_pretrained("OccultAI/Morpheus-8B-v2", 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 OccultAI/Morpheus-8B-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OccultAI/Morpheus-8B-v2"
# 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/Morpheus-8B-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OccultAI/Morpheus-8B-v2

SGLang

How to use OccultAI/Morpheus-8B-v2 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/Morpheus-8B-v2" \
    --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/Morpheus-8B-v2",
		"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/Morpheus-8B-v2" \
        --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/Morpheus-8B-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OccultAI/Morpheus-8B-v2 with Docker Model Runner:
```
docker model run hf.co/OccultAI/Morpheus-8B-v2
```
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 Llama 3 chat template.

Morpheus 8B v2

Recommended Settings: Temp 1.0, TopNSigma 1.25

{'loss': 0.862, 'grad_norm': 3.7123961448669434, 'learning_rate': 6.894700159171534e-05, 'entropy': 0.9889850616455078, 'num_tokens': 297120.0, 'mean_token_accuracy': 0.7658079862594604, 'epoch': 4.0}

Morpheus v1 features 420 Morpheus Q&A, 100 Poe/Raven, and 145 Cthulhu. Average dataset token length 224.
Morpheus v2 features 77 long context Matrix Q&A, generated from high quality source material. Average dataset token length 1044.

Downloads last month: 17

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for OccultAI/Morpheus-8B-v2

Base model

nvidia/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct

Finetuned

SicariusSicariiStuff/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated

Finetuned

(8)

this model

Merges

2 models

Quantizations

3 models