Instructions to use QuixiAI/WizardLM-7B-Uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuixiAI/WizardLM-7B-Uncensored with Transformers:

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

pipe = pipeline("text-generation", model="QuixiAI/WizardLM-7B-Uncensored")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QuixiAI/WizardLM-7B-Uncensored")
model = AutoModelForCausalLM.from_pretrained("QuixiAI/WizardLM-7B-Uncensored")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use QuixiAI/WizardLM-7B-Uncensored with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/QuixiAI/WizardLM-7B-Uncensored

SGLang

How to use QuixiAI/WizardLM-7B-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-7B-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-7B-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-7B-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-7B-Uncensored",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use QuixiAI/WizardLM-7B-Uncensored with Docker Model Runner:
```
docker model run hf.co/QuixiAI/WizardLM-7B-Uncensored
```

Am I overthinking this?

#17

by GaaraOtheSand - opened May 25, 2023

Discussion

GaaraOtheSand

May 25, 2023

I'm finding myself stuck on how to implement this into my script, I figure that you could simply do it like other models but I'd like to make sure, this is how I'd imagine you can run it:

config = transformers.AutoConfig.from_pretrained(
  'ehartford/WizardLM-7B-Uncensored',
  trust_remote_code=True
)

config.attn_config['attn_impl'] = 'torch'

config.update({"max_seq_len": 8192})

model = transformers.AutoModelForCausalLM.from_pretrained(
  'ehartford/WizardLM-7B-Uncensored',
  config=config,
  torch_dtype=torch.bfloat16,
  trust_remote_code=True
)

Although, I'm uncertain about things like if I can actually change the sequence length on this one, and if I need to add the attn_config part. Any help would greatly be appreciated.

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