Instructions to use WizardLMTeam/WizardLM-13B-V1.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WizardLMTeam/WizardLM-13B-V1.2 with Transformers:

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

pipe = pipeline("text-generation", model="WizardLMTeam/WizardLM-13B-V1.2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WizardLMTeam/WizardLM-13B-V1.2")
model = AutoModelForCausalLM.from_pretrained("WizardLMTeam/WizardLM-13B-V1.2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use WizardLMTeam/WizardLM-13B-V1.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WizardLMTeam/WizardLM-13B-V1.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WizardLMTeam/WizardLM-13B-V1.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/WizardLMTeam/WizardLM-13B-V1.2

SGLang

How to use WizardLMTeam/WizardLM-13B-V1.2 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 "WizardLMTeam/WizardLM-13B-V1.2" \
    --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": "WizardLMTeam/WizardLM-13B-V1.2",
		"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 "WizardLMTeam/WizardLM-13B-V1.2" \
        --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": "WizardLMTeam/WizardLM-13B-V1.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WizardLMTeam/WizardLM-13B-V1.2 with Docker Model Runner:
```
docker model run hf.co/WizardLMTeam/WizardLM-13B-V1.2
```

What is the prompt format?

by TheBloke - opened Jul 26, 2023

Discussion

TheBloke

Jul 26, 2023

Thanks for the great release!

Could you please clarify the prompt template?

For WizardLM V1.0 13B and 30B you had Vicuna style:

A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: hello, who are you? ASSISTANT:

For the earlier WizardLM V1.0 7B you had Alpaca style:

"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"

I assumed that this was Vicuna, as that is what you used most recently.

But someone is telling me that Alpaca is working better.

It would be great to get confirmation of the official intended prompt template?

Thanks again for all your great models.

dranger003

Jul 27, 2023

Looks like you have the right prompt @TheBloke as it is the same in their repo:
https://github.com/nlpxucan/WizardLM/blob/main/WizardLM/src/infer_wizardlm13b.py#L79

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