Instructions to use Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b with Transformers:

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

pipe = pipeline("text-generation", model="Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b")
model = AutoModelForCausalLM.from_pretrained("Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b

SGLang

How to use Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b 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 "Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b" \
    --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": "Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b",
		"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 "Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b" \
        --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": "Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b with Docker Model Runner:
```
docker model run hf.co/Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b
```

Question

by dondre - opened Jun 9, 2023

Discussion

dondre

Jun 9, 2023

Wish I could test out this model but it needs a A100 to load.
What kind of setup do you have?
Your models are great but with only 48GB VRAM i'm on the outside looking in.
Can you add some inference examples to these larger models?

Cebtenzzre

Jun 11, 2023

There are quantizations available that don't need as much VRAM:
https://huggingface.co/TheBloke/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-GPTQ
https://huggingface.co/TheBloke/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-GGML

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