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

Libraries

How to use HuggingFaceH4/starchat-beta with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/starchat-beta")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceH4/starchat-beta")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HuggingFaceH4/starchat-beta with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceH4/starchat-beta"
# 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-beta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

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

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

The inference api returns inComplete response

by aidan377 - opened Jun 19, 2023

Discussion

aidan377

Jun 19, 2023

When I use the inference api,it return very short answer,can you help to figure out the reason?Do I use wrong code?
The code to request:

prompt_template = "<|system|>\n<|end|>\n<|user|>\n{query}<|end|>\n<|assistant|>"
prompt = prompt_template.format(query="How do I sort a list in Python?")
# print(prompt)

output = query({
    "inputs": prompt,
    "parameters":{
        "max_new_token":256,
        "temperature":0.2,
        "do_sample":True,
        "top_k":50,
        "top_p":0.95,
        "eos_token_id":49155,
        "return_full_text":False
    }
})

The response:

[{'generated_text': '\nThere are multiple ways to sort a list in Python. One of the most common ways is to'}]

heifongni

Jun 21, 2023

try to use "return_full_text":True

aidan377

Aug 13, 2023

try to use "return_full_text":True

I have tried，the same results.Is there any limitation of api usage?

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