Instructions to use TheBloke/WizardLM-30B-Uncensored-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/WizardLM-30B-Uncensored-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/WizardLM-30B-Uncensored-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/WizardLM-30B-Uncensored-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/WizardLM-30B-Uncensored-GPTQ")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TheBloke/WizardLM-30B-Uncensored-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/WizardLM-30B-Uncensored-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-30B-Uncensored-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/WizardLM-30B-Uncensored-GPTQ

SGLang

How to use TheBloke/WizardLM-30B-Uncensored-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-30B-Uncensored-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-30B-Uncensored-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-30B-Uncensored-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-30B-Uncensored-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/WizardLM-30B-Uncensored-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/WizardLM-30B-Uncensored-GPTQ
```

Model Performance Curiosity

by sumuks - opened May 24, 2023

Discussion

sumuks

May 24, 2023

Hey Tom!

Thank you so much for the work that you're doing.

As title. With a powerful enough card (for context, 24G VRAM), would it make more sense to run an unquantized 13B parameter model, or a 4bit quantized 30B model? I think this question actually translates to - how much does quantization affect performance.

I've seen some of the synthetic benchmarks and perplexity scores, but I know that doesn't usually translate 1-1 for real world tasks. I also don't see a lot of evaluations done from an open ended content generation perspective, so I'd love any anecdotal evidence that you may have come across.

Thank you once again!

Llacer

May 24, 2023

Just try both and see what you like. Why would you have to ask this? If you have the hardware just try them with your own benchmarks.

sumuks

May 24, 2023

In my experience, benchmark performance has not exactly been perfectly correlated with real world performance. I remember @TheBloke mentioning in another discussion (perhaps on a different release), that he had some experience with this, so I was curious regarding his thought process.

That being said, I'm also planning to conduct some research on some metrics to evaluate open ended content generation, (perhaps something like https://aclanthology.org/2021.acl-long.500.pdf )

MihailRus

Jul 11, 2023

sumuks, could you tell us what is more productive in the end?

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