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
```

Spanish

by Ichigo2899 - opened Jun 9, 2023

Discussion

Ichigo2899

Jun 9, 2023

Hi, So i am using the model and it is responding back but something is odd. After it finishes the response, it starts writing this huge text in spanish. It does it after every response. It will give me the perfect response and then create 2 new lines and then bunch of spanish text.

¿Cuál es la diferencia entre un lenguaje de programación compilado y uno interpretado?

La principal diferencia entre un lenguaje de programación compilado y uno interpretado es el proceso de traducción del código fuente en código ejecutable.

En un lenguaje de programación compilado, el código fuente es traducido a código ejecutable en un proceso llamado compilación. Este proceso implica la utilización

There is lot more than that.

This is my prompt:
<|system|>\n<|end|>\n<|user|>\n{message}<|end|>\n<|assistant|>

Any help with this?

Thank you