Not-For-All-Audiences

nsfw

Instructions to use NeverSleep/Lumimaid-v0.2-123B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NeverSleep/Lumimaid-v0.2-123B with Transformers:

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

pipe = pipeline("text-generation", model="NeverSleep/Lumimaid-v0.2-123B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NeverSleep/Lumimaid-v0.2-123B")
model = AutoModelForCausalLM.from_pretrained("NeverSleep/Lumimaid-v0.2-123B")
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 NeverSleep/Lumimaid-v0.2-123B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NeverSleep/Lumimaid-v0.2-123B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeverSleep/Lumimaid-v0.2-123B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NeverSleep/Lumimaid-v0.2-123B

SGLang

How to use NeverSleep/Lumimaid-v0.2-123B 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 "NeverSleep/Lumimaid-v0.2-123B" \
    --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": "NeverSleep/Lumimaid-v0.2-123B",
		"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 "NeverSleep/Lumimaid-v0.2-123B" \
        --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": "NeverSleep/Lumimaid-v0.2-123B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NeverSleep/Lumimaid-v0.2-123B with Docker Model Runner:
```
docker model run hf.co/NeverSleep/Lumimaid-v0.2-123B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Lumimaid 0.2

8b - 12b - 70b - [123b]

This model is based on: Mistral-Large-Instruct

Wandb: https://wandb.ai/undis95/Lumi-Mistral-Large?nw=nwuserundis95

Lumimaid 0.1 -> 0.2 is a HUGE step up dataset wise.

As some people have told us our models are sloppy, Ikari decided to say fuck it and literally nuke all chats out with most slop.

Our dataset stayed the same since day one, we added data over time, cleaned them, and repeat. After not releasing model for a while because we were never satisfied, we think it's time to come back!