from transformers import pipeline

# Pipeline
pipe = pipeline(
    "text-generation",
    model="Bertug1911/Brion-1",
    trust_remote_code=True,
    top_k=40,              # Good for creativity
    temperature=0.8       # Good for creativity
    #max_new_tokens=512     # Default maximum model output (Maximum 1024)
)

# Messages
messages = [
    {"role": "user", "content": "What is the capital of France?"},
]

# Take out
output = pipe(messages)

# Only write asistant's (Model output) answer
assistant_response = output[0]["generated_text"][-1]["content"].strip()
# Special token conversions
formatted_out = assistant_response.replace(" ", "").replace("Ġ", " ").replace("Ċ", "\n")

print(formatted_out)