Why the imported fine tuned model not replying as it is responding in playground?

My fine tuned model is perfectly repsonding in the playground but not through the API. Please tell me how to resolve-
response = client.chat.completions.create(
model=“ft:gpt-3.5-turbo-1106:personal::8frqkawLD”,
messages=[
{“role”: “user”,
“content”: Body} # The role can be ‘system’, ‘user’, or ‘assistant’
],
temperature=1,
max_tokens=256,
top_p=1,
frequency_penalty=0,
presence_penalty=0

)

chat_response = response.choices[0].message.content.strip()

I have tried keeping the temp=0 also but this model on playground is responding perfectly fine but in the code in the application is messing up badly , how to make it produce the same responses as in the playground?

1 Like