Instructions to use Kooten/MiquMaid-v1-70B-6bpw-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kooten/MiquMaid-v1-70B-6bpw-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="Kooten/MiquMaid-v1-70B-6bpw-exl2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kooten/MiquMaid-v1-70B-6bpw-exl2")
model = AutoModelForCausalLM.from_pretrained("Kooten/MiquMaid-v1-70B-6bpw-exl2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Kooten/MiquMaid-v1-70B-6bpw-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kooten/MiquMaid-v1-70B-6bpw-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kooten/MiquMaid-v1-70B-6bpw-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Kooten/MiquMaid-v1-70B-6bpw-exl2

SGLang

How to use Kooten/MiquMaid-v1-70B-6bpw-exl2 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 "Kooten/MiquMaid-v1-70B-6bpw-exl2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kooten/MiquMaid-v1-70B-6bpw-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Kooten/MiquMaid-v1-70B-6bpw-exl2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kooten/MiquMaid-v1-70B-6bpw-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Kooten/MiquMaid-v1-70B-6bpw-exl2 with Docker Model Runner:
```
docker model run hf.co/Kooten/MiquMaid-v1-70B-6bpw-exl2
```

can i request 8bpw?

by Perpetuity7 - opened Feb 3, 2024

Discussion

Perpetuity7

Feb 3, 2024

•

edited Feb 3, 2024

i can use 70b 8bpw models using 4x 3090, 96GB VRAM

Kooten

Owner Feb 3, 2024

Of course.
Here you go

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