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
```

Thank You!

by playcrackthesky - opened Mar 13, 2024

Discussion

playcrackthesky

Mar 13, 2024

I have tested 100's of models and this is one of the special ones. Whether it's application for work, general knowledge, RP, ERP; it's special. Last night, during an RP, it broke character and the 4th wall, and gave me feedback on the entire roleplay scenario, which is something I have never had happen with any model.

My Settings-
temp: 1.75
top_p: 0.9
min_p: 0.2
top_k: 20
rep_penalty: 1.05
temperature_last

sophosympatheia

Owner Mar 14, 2024

I'm glad you're enjoying it! I like a model being able to break character (at least when prompted) in order to comment on the story, and I actually do test for that capability.

Interesting sampler settings. Do you find that setting top_p and top_k delivers better results than leaving them off and just using min_p?

playcrackthesky

Mar 14, 2024

Still great results with top_k and top_p off. It seems to be a little more deterministic that way, but still great.

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