Instructions to use TheBloke/wizardLM-7B-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/wizardLM-7B-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/wizardLM-7B-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/wizardLM-7B-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/wizardLM-7B-GPTQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/wizardLM-7B-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/wizardLM-7B-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-7B-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/wizardLM-7B-GPTQ

SGLang

How to use TheBloke/wizardLM-7B-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-7B-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-7B-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-7B-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-7B-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/wizardLM-7B-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/wizardLM-7B-GPTQ
```

text-generation-webui doesn't launch

by ryryry22 - opened Apr 28, 2023

Discussion

ryryry22

Apr 28, 2023

•

edited Apr 29, 2023

I get this :( I notice a little bump in RAM but nothing happens. Any idea why? Any tips? I am using the -no act model, and the vicuna 7b loads if I set my page file size to 100 gb.

Update: I download the .pt model from this post:
https://huggingface.co/TheBloke/wizardLM-7B-GPTQ/discussions/6#644b1a6e3a619fe72b17af1e
that model works but not the .safetensors file...
So if anyone is having the same problem use the .pt file :)

TheBloke

Owner Apr 29, 2023

Sorry not to get back to you.

The compat.no-act-order.safetensors files from my repo should work for you in text-generation-webui. I'm not sure why it didn't.

But if the other file works for you then fair enough!

ryryry22

May 1, 2023

Thank you for the time, don't worry. And thank you for your models.
I have just downloaded and try the compat.no-act-order.safetensors one, to be sure, but it doesn't load. Again a small bump in RAM but just that. It is like it is trying to load it but then the process stops. It is very strange, but yes, I think the program just want .pt files and hates .safetensors hahahahaha filefobic... Have a great day! Thank you for your time and don't stop converting models :)

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