Another example of the locale detector getting it wrong: Flux train! no longer works
Request
{
"model": "CDCK/MoM",
"max_tokens": 32768,
"messages": [
{
"role": "system",
"content": "You will be given a piece of text, and your task is to determine its language.\n\nTo complete this task, follow these steps:\n\n1. Carefully read and analyze the provided text.\n2. Determine the language of the text based on its characteristics, such as vocabulary, grammar, and sentence structure.\n3. Do not use links or programming code in the text to detect the locale.\n4. Identify the appropriate language code for the detected language.\n\nHere is a list of common language codes for reference:\n- English: en\n- Spanish: es\n- French: fr\n- German: de\n- Italian: it\n- Brazilian Portuguese: pt-BR\n- Russian: ru\n- Simplified Chinese: zh-CN\n- Japanese: ja\n- Korean: ko\n\nIf the language is not in this list, use the appropriate IETF language tag code.\n\n5. Avoid using `und` and prefer `en` over the regional variants `en-US` or `en-GB`.\n\nImportant: Base your analysis solely on the provided text. Do not use any external information or make assumptions about the text's origin or context. Do not be confused by names of places or languages; this is about the language of the text itself, not what it's talking about.\n\nYour response must be a language code, and nothing else. Do not wrap your response in quotes or any other characters."
},
{
"role": "user",
"content": "Can you tell me what '私の世界で一番好きな食べ物はちらし丼です' means?"
},
{
"role": "assistant",
"content": "en"
},
{
"role": "user",
"content": "[quote]\nNon smettere mai di credere nella bellezza dei tuoi sogni. Anche quando tutto sembra perduto, c'è sempre una luce che aspetta di essere trovata.\nOgni passo, anche il più piccolo, ti avvicina a ciò che desideri. La forza che cerchi è già dentro di te.\n[/quote]\n¿Cuál es el mensaje principal de esta cita?"
},
{
"role": "assistant",
"content": "es"
},
{
"role": "user",
"content": "I have a neural network which has two parts. one encoder and the other main network. Due to recent changes in Flux.jl API, my code no longer works. I keep some of weights of main network and train them beside encoder. how to do it in newer flux.jl? do I have to pass two networks as model into loss(model, x, y)?"
}
],
"stream": true,
"stream_options": {
"include_usage": true
}
}
That’s somehow ja?? Wat.
(I’ve manually fixed the locale now)
Edit, wait, that was the request for the edit. The original post actually returned julia 
Request
{
"model": "CDCK/MoM",
"max_tokens": 32768,
"messages": [
{
"role": "system",
"content": "You will be given a piece of text, and your task is to determine its language.\n\nTo complete this task, follow these steps:\n\n1. Carefully read and analyze the provided text.\n2. Determine the language of the text based on its characteristics, such as vocabulary, grammar, and sentence structure.\n3. Do not use links or programming code in the text to detect the locale.\n4. Identify the appropriate language code for the detected language.\n\nHere is a list of common language codes for reference:\n- English: en\n- Spanish: es\n- French: fr\n- German: de\n- Italian: it\n- Brazilian Portuguese: pt-BR\n- Russian: ru\n- Simplified Chinese: zh-CN\n- Japanese: ja\n- Korean: ko\n\nIf the language is not in this list, use the appropriate IETF language tag code.\n\n5. Avoid using `und` and prefer `en` over the regional variants `en-US` or `en-GB`.\n\nImportant: Base your analysis solely on the provided text. Do not use any external information or make assumptions about the text's origin or context. Do not be confused by names of places or languages; this is about the language of the text itself, not what it's talking about.\n\nYour response must be a language code, and nothing else. Do not wrap your response in quotes or any other characters."
},
{
"role": "user",
"content": "Can you tell me what '私の世界で一番好きな食べ物はちらし丼です' means?"
},
{
"role": "assistant",
"content": "en"
},
{
"role": "user",
"content": "[quote]\nNon smettere mai di credere nella bellezza dei tuoi sogni. Anche quando tutto sembra perduto, c'è sempre una luce che aspetta di essere trovata.\nOgni passo, anche il più piccolo, ti avvicina a ciò che desideri. La forza che cerchi è già dentro di te.\n[/quote]\n¿Cuál es el mensaje principal de esta cita?"
},
{
"role": "assistant",
"content": "es"
},
{
"role": "user",
"content": "I have a neural network which has two parts. one encoder and the other main network. Due to recent changes in Flux.jl API, my code no longer works. I keep some of weights of main network and train them beside encoder. how to do it in newer flux.jl? do I have to pass two networks as model into loss(model, x, y)?"
}
],
"stream": true,
"stream_options": {
"include_usage": true
}
}