Instructions to use HuggingFaceH4/starchat-alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceH4/starchat-alpha with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceH4/starchat-alpha")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/starchat-alpha")
model = AutoModelForMultimodalLM.from_pretrained("HuggingFaceH4/starchat-alpha")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HuggingFaceH4/starchat-alpha with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceH4/starchat-alpha"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceH4/starchat-alpha",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HuggingFaceH4/starchat-alpha

SGLang

How to use HuggingFaceH4/starchat-alpha 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/starchat-alpha" \
    --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": "HuggingFaceH4/starchat-alpha",
		"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 "HuggingFaceH4/starchat-alpha" \
        --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": "HuggingFaceH4/starchat-alpha",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceH4/starchat-alpha with Docker Model Runner:
```
docker model run hf.co/HuggingFaceH4/starchat-alpha
```

Can you share the server code for local deploy?

by merlinarer - opened May 13, 2023

Discussion

merlinarer

May 13, 2023

•

edited May 13, 2023

Thanks for the nice work! I want to deploy the chat model in my GPUs with your palyground, while I fail to process the stream properly. Can you share the server code that process the prompt and return stream ?
I use the following code:

    output = ""
    stream = pipe(prompt)
    for idx, response in enumerate(stream):
        output += response['generated_text'].replace(prompt, '')
        if idx == 0:
            history.append(" " + output)
        else:
            history[-1] = output
        chat = [(history[i].strip(), history[i + 1].strip()) for i in range(0, len(history) - 1, 2)]
        yield chat, history, user_message, ""

while it can only respose in first time and got nothing after that. I check it and find that, everytime the pipe just generate a /n after prompt and that is why user got nothing .

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