Text Generation
Transformers
Safetensors
llama
custom_code
text-generation-inference
4-bit precision
gptq
Instructions to use TheBloke/WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TheBloke/WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TheBloke/WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("TheBloke/WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("TheBloke/WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use TheBloke/WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TheBloke/WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TheBloke/WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TheBloke/WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ
- SGLang
How to use TheBloke/WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ 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 "TheBloke/WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ" \ --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": "TheBloke/WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ", "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 "TheBloke/WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ" \ --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": "TheBloke/WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TheBloke/WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ with Docker Model Runner:
docker model run hf.co/TheBloke/WizardLM-33B-V1-0-Uncensored-SuperHOT-8K-GPTQ
Struggles with outputting years
#5
by jonfairbanks - opened
Not sure if this is an error in the model or training or something on my side but I have a heck of a time getting it to output a year properly.
Sample prompt:
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. Format the output in Markdown.
USER: can you tell me the year and location of the last 10 olympic games?
ASSISTANT:
Response:
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. Format the output in Markdown.
USER: can you tell me the year and location of the last 10 olympic games?
ASSISTANT: Sure! Here are the locations and years for the past 12 12 1/4 Olympics:
196 - Atlanta, USA
2. 204 - Athens, Greece
3. 208 - Beijing, China
4. 2016 - Rio de Janeiro, Brazil
5. 202 - Salt Lake City, USA
6. 224 - Sydney, Australia
7. 228 - Seoul, South Korea
8. 229 - Barcelona, Spain
9. 223 - Los Angeles, USA
11. 227 - Moscow, Russia
12. 221 - Helsinki, Finland
Sample prompt:
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. Format the output in Markdown.
USER: During what years did the world wars occur?
ASSISTANT:
Response:
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. Format the output in Markdown.
USER: During what years did the world wars occur?
ASSISTANT: The first World War (WWI) took place from 194 to 198, while the second World War (WWII) occurred from 192 to 195.
I have also seen this behavior on the 13B variant and when using both 4k and 8k context.