Not-For-All-Audiences

nsfw

Instructions to use Netrve/Miqu-PlayMaid-2x70B-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Netrve/Miqu-PlayMaid-2x70B-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="Netrve/Miqu-PlayMaid-2x70B-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Netrve/Miqu-PlayMaid-2x70B-v0.1")
model = AutoModelForCausalLM.from_pretrained("Netrve/Miqu-PlayMaid-2x70B-v0.1")
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 Netrve/Miqu-PlayMaid-2x70B-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Netrve/Miqu-PlayMaid-2x70B-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Netrve/Miqu-PlayMaid-2x70B-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Netrve/Miqu-PlayMaid-2x70B-v0.1

SGLang

How to use Netrve/Miqu-PlayMaid-2x70B-v0.1 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 "Netrve/Miqu-PlayMaid-2x70B-v0.1" \
    --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": "Netrve/Miqu-PlayMaid-2x70B-v0.1",
		"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 "Netrve/Miqu-PlayMaid-2x70B-v0.1" \
        --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": "Netrve/Miqu-PlayMaid-2x70B-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Netrve/Miqu-PlayMaid-2x70B-v0.1 with Docker Model Runner:
```
docker model run hf.co/Netrve/Miqu-PlayMaid-2x70B-v0.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Miqu PlayMaid 2x70B v0.1

Image to be replaced :P

This model uses the Alpaca prompting format. Unlike the base model this one is tuned on 16384 sequence length. This was due to memory constraints.

Like Undi and Ikari, I followed my finetune up by making a MoE, made of Miqu PlayMaid 70B and Miqu 70B DPO.

Miqu PlayMaid 70B a roleplay focused finetune using MiquMaid v2 70B DPO by Undi95 and IkariDev as base.

My goal was to further push MiquMaid into creative writing and roleplay, hopefully adding some spice to it.

Credits:

Netrve
Special thanks to everyone on TheBloke's Discord who helped me!

Credits for MiquMaid:

Undi
IkariDev

Description

This repo contains the BF16 files of Miqu-PlayMaid-2x70B-v0.1

Training data used:

Format:

I can only guarantee that it works with a maximum context length of 16384. Might work with 32768, but no promises.

### Instruction:
{system prompt}
### Input:
{input}
### Response:
{reply}

Support

Netrve: If you like what I did, feel free to support future work here

Don't forget to send some love to the original masterminds behind MiquMaid:

Undi: If you want to support us, you can here
IkariDev: Visit my retro/neocities style website please kek

Downloads last month: 3

Safetensors

Model size

125B params

Tensor type

BF16

Model tree for Netrve/Miqu-PlayMaid-2x70B-v0.1

Quantizations

2 models