Instructions to use QuixiAI/Wizard-Vicuna-7B-Uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuixiAI/Wizard-Vicuna-7B-Uncensored with Transformers:

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

pipe = pipeline("text-generation", model="QuixiAI/Wizard-Vicuna-7B-Uncensored")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QuixiAI/Wizard-Vicuna-7B-Uncensored")
model = AutoModelForCausalLM.from_pretrained("QuixiAI/Wizard-Vicuna-7B-Uncensored", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use QuixiAI/Wizard-Vicuna-7B-Uncensored with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuixiAI/Wizard-Vicuna-7B-Uncensored"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuixiAI/Wizard-Vicuna-7B-Uncensored",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/QuixiAI/Wizard-Vicuna-7B-Uncensored

SGLang

How to use QuixiAI/Wizard-Vicuna-7B-Uncensored 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 "QuixiAI/Wizard-Vicuna-7B-Uncensored" \
    --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": "QuixiAI/Wizard-Vicuna-7B-Uncensored",
		"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 "QuixiAI/Wizard-Vicuna-7B-Uncensored" \
        --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": "QuixiAI/Wizard-Vicuna-7B-Uncensored",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use QuixiAI/Wizard-Vicuna-7B-Uncensored with Docker Model Runner:
```
docker model run hf.co/QuixiAI/Wizard-Vicuna-7B-Uncensored
```

License?

by kobolventures - opened May 20, 2023

Discussion

kobolventures

May 20, 2023

Hi, I'm curious what the license is of this model. Can it be used in commercial applicatons?

ehartford

Quixi AI org May 20, 2023

It's based on llama. I don't think Facebook is gonna sue anyone

Also it's uncensored. I recommend you put an alignment layer before exposing it to anyone

KamiRaptor

Mar 28, 2025

What about commercial usage?

erichartford

Mar 28, 2025

From a legal perspective - this was trained on leaked llama weights, with no license. At the time, Meta had not released Llama.

Now they have released Llama 2 and Llama 3, I think it's safe to presume the latest Llama license.

From a practical perspective - you shouldn't use this model for anything but research and historical. There are much better models these days. if you are looking for the 7b-9b range, consider Llama 3.1 8b, Qwen2.5 7b, or Gemma3 4b or 12b (an "ablated" or finetune)

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