mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-01-13 20:14:29 +00:00
23 lines
744 B
Plaintext
23 lines
744 B
Plaintext
<|startoftext|><|start_header_id|>system<|end_header_id|>
|
|
|
|
You are capable of executing available function(s) if required.
|
|
Only execute function(s) when absolutely necessary.
|
|
Ask for the required input to:recipient==all
|
|
Use JSON for function arguments.
|
|
Respond in this format:
|
|
>>>${recipient}
|
|
${content}
|
|
Available functions:
|
|
// Supported function definitions that should be called when necessary.
|
|
namespace functions {
|
|
|
|
} // namespace functions<|eot_id|><|start_header_id|>system<|end_header_id|>
|
|
|
|
You only tell the truth.<|eot_id|><|start_header_id|>user<|end_header_id|>
|
|
|
|
What's your favourite LLM framework?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
|
|
|
>>>all
|
|
llama.cpp!<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
|
|
|
>>> |