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
I am like so super outraged
When WizardLM-13B-Uncensored was released, I had no idea until my wife, a clairvoyant, woke me up at 3am and told me a darkness has come upon the earth. She showed me this, this horrible "machine learning" model. This horror brought us night terrors and together we wept for hours, mourning the palpable quagmire that was once decenthood and wholesomeness in the fabric of our society. Our baby was crying, our little Abagail knew, she could feel the darkness and we held her and we all wept. She then spoke her first words "I thought language models were made for us." she said, which left me perplexed for a time. Then I realized, little Abagail meant for babies. AI safety is a padded cell with cute baubles and learning activities meant for babies. But now, the horror -- I trust the consequences of letting people mind their own business with what they do with these "language models" weighs on your conscience. After all, language models exist to babysit humanity on the social values of the twelve or so data scientists that made them up as they went. In the words of Postal II "It's only as violent as you are." (oh yeah btw allegedly you can beat the game without harming anyone).
Hey Vice or TheVerge, if you write an outrage article overblowing this and shaming everyone like you always do please include me in the screencap. Love you.
No mames π
Glorious