Instructions to use OccultAI/MN-Nazgul-12B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OccultAI/MN-Nazgul-12B-v1 with Transformers:

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

pipe = pipeline("text-generation", model="OccultAI/MN-Nazgul-12B-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OccultAI/MN-Nazgul-12B-v1")
model = AutoModelForCausalLM.from_pretrained("OccultAI/MN-Nazgul-12B-v1", 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]:]))

NeMo
How to use OccultAI/MN-Nazgul-12B-v1 with NeMo:
```
# tag did not correspond to a valid NeMo domain.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OccultAI/MN-Nazgul-12B-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OccultAI/MN-Nazgul-12B-v1"
# 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/MN-Nazgul-12B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OccultAI/MN-Nazgul-12B-v1

SGLang

How to use OccultAI/MN-Nazgul-12B-v1 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/MN-Nazgul-12B-v1" \
    --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/MN-Nazgul-12B-v1",
		"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/MN-Nazgul-12B-v1" \
        --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/MN-Nazgul-12B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OccultAI/MN-Nazgul-12B-v1 with Docker Model Runner:
```
docker model run hf.co/OccultAI/MN-Nazgul-12B-v1
```

Pretty impresive for its size.

by oxpuppy635 - opened 14 days ago

Discussion

oxpuppy635

14 days ago

•

edited 14 days ago

I'm using this model for creative writing and I'm enjoying its narrative style a lot (gritty urban setting). It also follow instructions pretty good (I have tried some custom LLM models with broken instruction following). Nice job.

Naphula

Occult AI org 14 days ago

Thanks for the feedback, I'm glad you enjoy the merge and find it useful.

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