Text-Davinci-003 Model Not Producing Correct Result

API
1

I am using the model for reproducing step by step solution to a simple math question. For instance, I asked this question: “Show me how to solve the equation, x + 6x = 9.”. The model gave me a wrong answer.

image
image499×681 15.1 KB

You can go www.mylearnmate.com website to test it out.

I used this function to produce the steps:

def get_answer(text):
start_sequence = “\nAI:”
restart_sequence = "\nHuman: "

response = openai.Completion.create(
  model="text-davinci-003",
  prompt=f"{text} Show the steps.",
  temperature=0.9,
  max_tokens=150,
  top_p=1,
  frequency_penalty=0,
  presence_penalty=0.6,
  stop=[" Human:", " AI:"]
)
return response.choices[0].text.strip()

Please let me know how to improve the model.

Thanks,

Onur

2

More threads available. The little magnifying glass on top is a search button.

Hope this helps!

3

I am sorry the thread doesn’t apply to my case because I don’t have a ChatGPT API which is not available yet.

4

Sorry. I just meant in general this topic has been covered before.

That is, calculations are a known weak point for large language models.

5

Is there any other mode that you recommend me to use which is not large language model?

6

Not off hand. What are you trying to accomplish?

Where else have you searched so far on your journey?

7

Wolfram alpha is a better alternative. But it is not ChatGPT or GPT related.

8

I was getting the details while @raymonddavey was posting.

Since the link gets corruped when posting here are the steps.

  1. Naviage to Wolfram|Alpha
  2. In text enter x + 6x = 9 simplify
  3. Press enter
9

WolframAlpha is good but I want to extract information about the question such as question type linear equation or something else. That information is used later in video generations. WolframAlpha is not flexible but I might need to use two APIs: GPT and WolframAlpha that might resolve my issue.

Thanks for the replies.