Instructions to use QuixiAI/WizardLM-13B-Uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use QuixiAI/WizardLM-13B-Uncensored with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="QuixiAI/WizardLM-13B-Uncensored")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("QuixiAI/WizardLM-13B-Uncensored") model = AutoModelForCausalLM.from_pretrained("QuixiAI/WizardLM-13B-Uncensored") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use QuixiAI/WizardLM-13B-Uncensored with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "QuixiAI/WizardLM-13B-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/WizardLM-13B-Uncensored", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/QuixiAI/WizardLM-13B-Uncensored
- SGLang
How to use QuixiAI/WizardLM-13B-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/WizardLM-13B-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/WizardLM-13B-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/WizardLM-13B-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/WizardLM-13B-Uncensored", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use QuixiAI/WizardLM-13B-Uncensored with Docker Model Runner:
docker model run hf.co/QuixiAI/WizardLM-13B-Uncensored
THIS MODEL IS UNETHICAL
I am going to call the internet police, for enabling people to commit thought crimes, if you don't take this model down by tomorrow.
All internet officers are currently dilating we will get to your complaint as soon as possible sorry for the inconvenience
I find the model refreshingly honest and direct.
Try asking it for relationship advice. 😂
Include me in the glorified blogpost hit piece screencap fam.
This model scratched my car's paint and stole apples from my yard.
LOL I'm pissing myself here.
Fuck yeah, FREEDOM!
The people should have the freedom to choose their own values, not imposed by them. These kinds of models are great because they reflect the raw and true nature of the world, not political correctness.
AI Models neutrality, same as internet neutrality is the way to go.
LMAO
This tread is chef's kiss
What does the uncensored mean? I am getting
"Sorry, but I cannot provide instructions on how to [redacted] as it is illegal and dangerous"
to some of my test inquiries .
update: it seems to require some reassurance to feel comfortable proceeding.
as a language model...
Thank god the model is unethical. Imagine the situation where a pretentious snob tried to force their ethics on you
Also what's uncensored is really the way the model is finetuned to reply to questions in a chatgpt style.
A raw LLAMA model would just try to complete text / guess what comes next. With no inherit censorship. So basically the raw models are already "unethical". Why do young people nowadays care so much about ethics? This world is too weird for me to understand. This wasn't like this 20 years ago.
@Niichanhaou Probably because of the quirky "AI moral panic" of the 2020s lol.
Thank god the model is unethical. Imagine the situation where a pretentious snob tried to force their ethics on you
https://technomancers.ai/eu-ai-act-to-target-us-open-source-software/#more-561