Non-ASCII characters break the output

[remixer-dec]

Hi, I tried the llama.cpp example and noticed that this library cannot handle non-ascii characters correctly by default and it stops right after running into such character.


Is it possible to allow these characters?

[noamgat]

Hi! This is indeed a current limitation of the library, I hope to address it soon.

[noamgat]

class AnswerFormat(BaseModel):
    emoji_strings: List[str]

question = 'What are the 10 most common emojis? You MUST answer using the following json schema: '

now leads to

  {
"emoji_strings": [
"😊",
"👍",
"🤣",
"🚀",
"🎉",
"❤️",
"🤔",
"🙏",
"💭",
"😢",
"😠"] }

[remixer-dec]

Amazing!