app.py

from huggingface_hub import InferenceClient
api_key=os.getenv("HF_TOKEN")
client = InferenceClient(api_key=api_key)

messages = [
	{ "role": "user", "content": "Tell me a story" }
]

stream = client.chat.completions.create(
    model="HuggingFaceH4/zephyr-7b-beta", 
	messages=messages, 
	temperature=0.5,
	max_tokens=2048,
	top_p=0.7,
	stream=True
)

for chunk in stream:
    print(chunk.choices[0].delta.content)