Instructions to use Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw with Transformers:

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

pipe = pipeline("text-generation", model="Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw")
model = AutoModelForCausalLM.from_pretrained("Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw")
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

vLLM

How to use Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw

SGLang

How to use Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw 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 "Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw" \
    --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": "Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw",
		"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 "Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw" \
        --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": "Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw with Docker Model Runner:
```
docker model run hf.co/Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw
```

Midnight-Miqu-103B-v1.0 - EXL2 3.5bpw

This is a 3.5bpw EXL2 quant of sophosympatheia/Midnight-Miqu-103B-v1.0

Details about the model and the merge info can be found at the above mode page.

Quant Details

This is the script used for quantization.

#!/bin/bash

# Activate the conda environment
source ~/miniconda3/etc/profile.d/conda.sh
conda activate exllamav2

# Define variables
MODEL_DIR="models/sophosympatheia_Midnight-Miqu-103B-v1.0"
OUTPUT_DIR="exl2_midnight103b"
MEASUREMENT_FILE="measurements/midnight103b.json"

BIT_PRECISION=3.5
CONVERTED_FOLDER="models/Midnight-Miqu-103B_exl2_3.5bpw"

# Create directories
mkdir $OUTPUT_DIR
mkdir $CONVERTED_FOLDER

# Run conversion commands
python convert.py -i $MODEL_DIR -o $OUTPUT_DIR -nr -om $MEASUREMENT_FILE
python convert.py -i $MODEL_DIR -o $OUTPUT_DIR -nr -m $MEASUREMENT_FILE -b $BIT_PRECISION -cf $CONVERTED_FOLDER

Downloads last month: 3

Collection including Dracones/Midnight-Miqu-103B-v1.0_exl2_3.5bpw

Midnight Miqu v1.0

Collection

Quants of Sophosympatheia's Midnight Miqu series of models. • 15 items • Updated Mar 14, 2024