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, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

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
```

General tips around inference speed?

by jloganolson - opened May 10, 2023

Discussion

jloganolson

May 10, 2023

Maybe I just haven't run this large of a model before but I'm blown away by the difference in speed for this 16b model versus a 12b parameter model like pythia. Are there any speed-up tips? Things I'm doing so far:

On pytorch 2.0
Confirmed it's running on CUDA (device=0 and VRAM is soaked)
torch_dtype=torch.bfloat16
even tried loading as 8 bit to no noticeable speed-up (but I guess that last one is more to alleviate memory than speed things up).

Any other ideas?

MichaelFried

May 11, 2023

•

edited May 11, 2023

Did pytorch 2.0 gave you noticable improvement?

jloganolson

May 12, 2023

I actually didn't try Pytorch 1.x so I don't know! The one last thing I was going to try was deepspeed inference (per this https://www.deepspeed.ai/tutorials/inference-tutorial/) but I don't know how much improvement I'm going to see on a single GPU machine.