Output
#139190
Replies: 1 comment
-
you can specify the desired format you're looking for and the structured output language (Markdown, JSON,..) or consider building a pipeline for fine-tuning the responses after generation |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Select Topic Area
Show & Tell
Body
Your response for all of models is not pretty enough can u use similar openai? Ex: {
"id": "cmpl-82b68197b48f4a66b4ff27e9de599175",
"object": "chat.completion",
"created": 1726836041,
"model": "Meta-Llama-3.1-70B-Instruct",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "The capital of France is Paris.",
"tool_calls": []
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 28,
"completion_tokens": 8,
"total_tokens": 36
}
} And even can change model name like instead Meta-Llama... Change Llama-3.1-70b-instruct
Beta Was this translation helpful? Give feedback.
All reactions