This is quantized version of [hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode](https://huggingface.co/hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode) created using llama.cpp
# >> {"message": "I am a helpful assistant, with access to a vast amount of information. I can help you with tasks such as answering questions, providing definitions, translating text, and more. Feel free to ask me anything!"}
{ "role": "system", "content": f"""You are a helpful assistant with access to the following functions: \n {str(functions_metadata)}\n\nTo use these functions respond with:\n<functioncall> {{ "name": "function_name", "arguments": {{ "arg_1": "value_1", "arg_1": "value_1", ... }} }} </functioncall>\n\nEdge cases you must handle:\n - If there are no functions that match the user request, you will respond politely that you cannot help."""},
{ "role": "user", "content": "What is the temperature in Tokyo right now?"}
{ "role": "system", "content": f"""You are a helpful assistant with access to the following functions: \n {str(functions_metadata)}\n\nTo use these functions respond with:\n<functioncall> {{ "name": "function_name", "arguments": {{ "arg_1": "value_1", "arg_1": "value_1", ... }} }} </functioncall>\n\nEdge cases you must handle:\n - If there are no functions that match the user request, you will respond politely that you cannot help."""},
{ "role": "user", "content": "What is the temperature in Tokyo right now?"},
# You will get the previous prediction, extract it will the tag <functioncall>
# execute the function and append it to the messages like below: