Instructions to use sophosympatheia/Midnight-Miqu-70B-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sophosympatheia/Midnight-Miqu-70B-v1.0 with Transformers:

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

pipe = pipeline("text-generation", model="sophosympatheia/Midnight-Miqu-70B-v1.0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sophosympatheia/Midnight-Miqu-70B-v1.0")
model = AutoModelForCausalLM.from_pretrained("sophosympatheia/Midnight-Miqu-70B-v1.0", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sophosympatheia/Midnight-Miqu-70B-v1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sophosympatheia/Midnight-Miqu-70B-v1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sophosympatheia/Midnight-Miqu-70B-v1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sophosympatheia/Midnight-Miqu-70B-v1.0

SGLang

How to use sophosympatheia/Midnight-Miqu-70B-v1.0 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 "sophosympatheia/Midnight-Miqu-70B-v1.0" \
    --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": "sophosympatheia/Midnight-Miqu-70B-v1.0",
		"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 "sophosympatheia/Midnight-Miqu-70B-v1.0" \
        --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": "sophosympatheia/Midnight-Miqu-70B-v1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sophosympatheia/Midnight-Miqu-70B-v1.0 with Docker Model Runner:
```
docker model run hf.co/sophosympatheia/Midnight-Miqu-70B-v1.0
```

Feedback

by Szarka - opened Mar 3, 2024

Discussion

Szarka

Mar 3, 2024

The original miqu censoring can be felt, like avoiding words and such. I'd recommend that you merge a miqu that's already finetuned like miqumaid, or something like that.

jackboot

Mar 3, 2024

please, no undi-slop. LZLV, euryale, anything else.

sophosympatheia

Owner Mar 3, 2024

@Szarka I'm impressed you found some words this model won't use. I'll give miqumaid another look. In my initial testing with it, it didn't merge as well and it struggled more with some logical tests, but that was before I tried the SLERP merge approach.

@jackboot What is undi-slop? Can you explain your comment?

Szarka

Mar 3, 2024

•

edited Mar 3, 2024

@sophosympatheia I mean... it can use them but it doesn't bring them up on it's own if you know what i mean

jackboot

Mar 3, 2024

I've seen the datasets Undi and crew used for these models (including the maids) and I'm not impressed. Lots of gpt-isms and low quality. The models aren't very intelligent but they are super geared towards easy NSFW so people like them. I think it's a mistake to merge them into this one. Uncensored isn't the only metric and as you see from your experience, they get dumb.

I have stacked miqu, senku, quartet against each other and yours is the least censored from the bunch. With a good system prompt, I hardly see any issues. Certainly not worth getting more shivers down your spine over.

sophosympatheia

Owner Mar 3, 2024

@jackboot I like your style haha. Thanks for engaging with my models and actively sharing your thoughts.

Szarka

Mar 3, 2024

@jackboot i see... In this case it's really not a good idea to merge it sorry. I agree if this is the case

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