Instructions to use ddh0/MiquSuperdark-70B-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ddh0/MiquSuperdark-70B-v2 with Transformers:

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

pipe = pipeline("text-generation", model="ddh0/MiquSuperdark-70B-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ddh0/MiquSuperdark-70B-v2")
model = AutoModelForCausalLM.from_pretrained("ddh0/MiquSuperdark-70B-v2")
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 ddh0/MiquSuperdark-70B-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ddh0/MiquSuperdark-70B-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ddh0/MiquSuperdark-70B-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ddh0/MiquSuperdark-70B-v2

SGLang

How to use ddh0/MiquSuperdark-70B-v2 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 "ddh0/MiquSuperdark-70B-v2" \
    --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": "ddh0/MiquSuperdark-70B-v2",
		"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 "ddh0/MiquSuperdark-70B-v2" \
        --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": "ddh0/MiquSuperdark-70B-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ddh0/MiquSuperdark-70B-v2 with Docker Model Runner:
```
docker model run hf.co/ddh0/MiquSuperdark-70B-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

MiquSuperdark-70B-v2

MiquSuperdark-70B-v2 is a merge of three of the most popular Miqu-derived models. The goal of the merge is to create an strong, well-rounded chat model that picks up desirable traits from its constituent models without sacrificing intelligence.

This is a linear merge with the following composition:

sophosympatheia/Midnight-Miqu-70B-v1.5 at weight 0.5
NeverSleep/MiquMaid-v3-70B at weight 0.3
maywell/miqu-evil-dpo at weight 0.2

Prompt format

The model responds well to general-purpose prompt formats such as Alpaca. Alternatively, I suggest trying the following format, replacing {the placeholder text} with your actual messages, without curly brackets.

<message from="system">{your system prompt here}</message><message from="user">{user prompt here}</message><message from="bot">{bot response here}</message><message from="user">{user prompt here}</message><message from="bot">{bot response here}</message> [... and so on ...]

This format is readily understood by the model, and leads to the expected high-quality responses. Note the lack of newlines \n - they are not necessary and might actually make it harder for the model to follow along.

Merge Configuration

The following YAML configuration was used to produce this model:

merge_method: linear
base_model: /media/dylan/SanDisk/LLMs/Midnight-Miqu-70B-v1.5
models:
- model: /media/dylan/SanDisk/LLMs/Midnight-Miqu-70B-v1.5
parameters:
weight: 0.5
- model: /home/dylan/Documents/AI/merge/MiquMaid-v3-70B
parameters:
weight: 0.3
- model: /media/dylan/SanDisk/LLMs/miqu-evil-dpo/
parameters:
weight: 0.2
dtype: float16

The tokenizer from 152334H/miqu-1-70b-sf is used.

Downloads last month: 2

Safetensors

Model size

69B params

Tensor type

F16

Model tree for ddh0/MiquSuperdark-70B-v2

NeverSleep/MiquMaid-v3-70B

maywell/miqu-evil-dpo

sophosympatheia/Midnight-Miqu-70B-v1.5

Merge model

this model

Quantizations

2 models