System role not supported Gemma 2

[rzafiamy]

Prerequisites

Please answer the following questions for yourself before submitting an issue.

• I am running the latest code. Development is very rapid so there are no tagged versions as of now.
• I carefully followed the README.md.
• [ X] I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
• [X ] I reviewed the Discussions, and have a new bug or useful enhancement to share.

Expected Behavior

I tried Gemma2 GGUF from hugging face. It is working fine with llama.cpp CLI on my PC.
However , I got issues while runing through llama-cpp-python package as follow :

self.llama = Llama(model_path=model_path, n_gpu_layers=n_gpu_layers, n_ctx=n_ctx, echo=echo, n_batch=n_batch,flash_attn=True)

messages = [
{
"role": "system",
"content": "You are a helpful assistant who perfectly reply to user request on the topic of Mistrious Dragon"
},
{
"role": "user",
"content": "Write a beautiful stroy for kids"
}
]

output = self.llama.create_chat_completion(messages,
temperature=temperature,
max_tokens=max_tokens,
top_p=1,
frequency_penalty=1.5,
presence_penalty=1.5)

Current Behavior

I got the following error:
......................python3.11/site-packages/llama_cpp/llama_chat_format.py", line 213, in raise_exception
raise ValueError(message)
ValueError: System role not supported

Environment and Context

I use python3.11 on ubuntu linux with CUDA enabled . > 24GB GPU RAM

[rzafiamy]

Solve it by adding chat_format:
self.llama = Llama(model_path=model_path,
n_gpu_layers=n_gpu_layers,
n_ctx=n_ctx,
echo=echo,
n_batch=n_batch,
flash_attn=True,
chat_format="gemma")

[rzafiamy]

I think it should be reworked finally. Stop token are not well managed and system role is not ok at all.