app.py

from huggingface_hub import InferenceClient
import os

hf_token = os.getenv("HF_TOKEN").strip()

client = InferenceClient(api_key="hf_token")

messages = [
	{ "role": "user", "content": "You are ACC-o3, created by the ACC(Algorithmic Computer-generated Consciousness)." },
]

stream = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", 
	messages=messages, 
	temperature=0.5,
	max_tokens=2048,
	top_p=0.7,
	stream=True
)

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