Not-For-All-Audiences

nsfw

Instructions to use NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS with Transformers:

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

pipe = pipeline("text-generation", model="NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS")
model = AutoModelForMultimodalLM.from_pretrained("NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS"
# 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/Llama-3-Lumimaid-8B-v0.1-OAS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS

SGLang

How to use NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS 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/Llama-3-Lumimaid-8B-v0.1-OAS" \
    --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/Llama-3-Lumimaid-8B-v0.1-OAS",
		"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/Llama-3-Lumimaid-8B-v0.1-OAS" \
        --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/Llama-3-Lumimaid-8B-v0.1-OAS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS with Docker Model Runner:
```
docker model run hf.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Lumimaid 0.1

This model uses the Llama3 prompting format

Llama3 trained on our RP datasets, we tried to have a balance between the ERP and the RP, not too horny, but just enough.

We also added some non-RP dataset, making the model less dumb overall. It should look like a 40%/60% ratio for Non-RP/RP+ERP data.

This model includes the new Luminae dataset from Ikari.

This model have received the Orthogonal Activation Steering treatment, meaning it will rarely refuse any request.

If you consider trying this model please give us some feedback either on the Community tab on hf or on our Discord Server.

Credits:

Undi
IkariDev

Description

This repo contains FP16 files of Lumimaid-8B-v0.1-OAS.

Switch: 8B - 70B - 70B-alt - 8B-OAS - 70B-OAS

Training data used:

Aesir datasets
NoRobots
limarp - 8k ctx
toxic-dpo-v0.1-sharegpt
ToxicQAFinal
Luminae-i1 (70B/70B-alt) (i2 was not existing when the 70b started training) | Luminae-i2 (8B) (this one gave better results on the 8b) - Ikari's Dataset
Squish42/bluemoon-fandom-1-1-rp-cleaned - 50% (randomly)
NobodyExistsOnTheInternet/PIPPAsharegptv2test - 5% (randomly)
cgato/SlimOrcaDedupCleaned - 5% (randomly)
Airoboros (reduced)
Capybara (reduced)

Models used (only for 8B)

Initial LumiMaid 8B Finetune
Undi95/Llama-3-Unholy-8B-e4
Undi95/Llama-3-LewdPlay-8B

Prompt template: Llama3

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{output}<|eot_id|>

Others

Undi: If you want to support us, you can here.

IkariDev: Visit my retro/neocities style website please kek

Downloads last month: 23

Safetensors

Model size

8B params

Tensor type

F16

Model tree for NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS

Merges

30 models

Quantizations

6 models

NeverSleep
/

Llama-3-Lumimaid-8B-v0.1-OAS