Instructions to use HuggingFaceH4/zephyr-7b-beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceH4/zephyr-7b-beta with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceH4/zephyr-7b-beta")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/zephyr-7b-beta")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceH4/zephyr-7b-beta")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HuggingFaceH4/zephyr-7b-beta with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceH4/zephyr-7b-beta"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceH4/zephyr-7b-beta",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HuggingFaceH4/zephyr-7b-beta

SGLang

How to use HuggingFaceH4/zephyr-7b-beta 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 "HuggingFaceH4/zephyr-7b-beta" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceH4/zephyr-7b-beta",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "HuggingFaceH4/zephyr-7b-beta" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceH4/zephyr-7b-beta",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HuggingFaceH4/zephyr-7b-beta with Docker Model Runner:
```
docker model run hf.co/HuggingFaceH4/zephyr-7b-beta
```

Free and ready to use zephyr-7B-beta-GGUF model as OpenAI API compatible endpoint

by limcheekin - opened Oct 28, 2023

Discussion

limcheekin

Oct 28, 2023

Hi there,

I deployed the model as OpenAI API compatible endpoint at https://huggingface.co/spaces/limcheekin/zephyr-7B-beta-GGUF.

If you find this resource valuable, your support in the form of starring the space would be greatly appreciated.

Thank you.

jontstaz

Nov 2, 2023

Hi, are you still maintaining this? I tried using it but it seems to time out/not return a response. Perhaps it's overloaded or some other issue. The only endpoint I can get to successfully return a response is the GET /v1/models. Thanks in advance,

limcheekin

Nov 2, 2023

I just tested with the API doc at https://huggingface.co/proxy/limcheekin-zephyr-7b-beta-gguf.hf.space/docs. It is working for a simple prompt.

If you use it for longer generation/response, you need to set stream=True.
Please refer to the following notebook at https://huggingface.co/spaces/limcheekin/Mistral-7B-Instruct-v0.1-GGUF/blob/main/mistral-7b-instruct.ipynb.

Hope this help.

limcheekin

Nov 6, 2023

Hi, are you still maintaining this? I tried using it but it seems to time out/not return a response. Perhaps it's overloaded or some other issue. The only endpoint I can get to successfully return a response is the GET /v1/models. Thanks in advance,

Added a jupyter notebook at https://huggingface.co/spaces/limcheekin/zephyr-7B-beta-GGUF/blob/main/zephyr-7b.ipynb

I hope this is helpful to you. :)

wengnews

Nov 19, 2023

How can I create my own o'penai API with zephyr-7b-beta and share your code? Thank you

limcheekin

Nov 19, 2023

You just need to select "Duplicate this Space" from the drop down menu.

All codes are located at https://huggingface.co/spaces/limcheekin/zephyr-7B-beta-GGUF/tree/main.

By the way, you can use git to clone the repo of the space.

I hope this helps and clarify.

wengnews

Nov 19, 2023

Thank you very much. I have just learned about Zephyr, and I have seen your way of using CPP. I would like to directly use Zephyr-7b-beta, while also implementing stream output.
I find ohter coder create api by using pipeline in the github,i want to use AutoModelForCausalLM.from_pretrained.

limcheekin

Nov 19, 2023

•

edited Nov 19, 2023

I didn't do that, can't help you. Appreciate your sharing if you managed to publish the api.

Thanks.

Hokk7

Dec 6, 2023

i got an error:
AuthenticationError: No API key provided. You can set your API key in code using 'openai.api_key = ', or you can set the environment variable OPENAI_API_KEY=). If your API key is stored in a file, you can point the openai module at it with 'openai.api_key_path =

limcheekin

Dec 6, 2023

i got an error:
AuthenticationError: No API key provided. You can set your API key in code using 'openai.api_key = ', or you can set the environment variable OPENAI_API_KEY=). If your API key is stored in a file, you can point the openai module at it with 'openai.api_key_path =

Set your HF token as the API key.

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