Task #3353
Updated by Ram Kordale 11 months ago
Change needed is only in ourPrompt and max_tokens.
Current call is:
POST /v1/completions {
"model": "text-davinci-003",
"prompt": <ourPrompt>,
"temperature": 0,
"max_tokens": 90, 60,
"top_p": 1,
"frequency_penalty": 0,
"presence_penalty": 0
}
Replace "text-davinci-003" with "gpt-3.5-turbo-instruct"