how to change the prompt template?

[bauerhartmut]

Hello,
When I run PHI3 with llama.cpp I get a weird output because it is using an output template:

<|assistant|> The sky appears blue to the human eye due to a phenomenon called Rayleigh scattering. When sunlight reaches Earth's atmosphere, it is made up of different colors of light, each with a different wavelength. Blue light has a shorter wavelength compared to other colors, which means it is scattered in all directions more than other colors when it interacts with the gas molecules in our atmosphere. This scattering of blue light is what gives the sky its blue appearance during the day.

I am using this code:

from llama_cpp import Llama
import torch

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(torch.cuda.is_available())

llm = Llama(
  model_path="Phi-3-mini-4k-instruct-q4.gguf",  # path to GGUF file
  n_ctx=4096,  # The max sequence length to use - note that longer sequence lengths require much more resources
  n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
  n_gpu_layers=35, # The number of layers to offload to GPU, if you have GPU acceleration available. Set to 0 if no GPU acceleration is available on your system.
  device="cuda:0"
)

prompt = "why is the sky blue?"

# Simple inference example
output = llm(
  prompt,
  max_tokens=512,  # Generate up to 512 tokens
  stop=["<|end|>"], 
  echo=False,  # Whether to echo the prompt
)

output = output['choices'][0]['text']

print(output)

How can I fix it that I get just the LLM output without or or something?