Can we create a private model based on davinci-instruct-beta-v3 using open AI's fine-tuning

zhengjin · April 29, 2023, 2:51am

In the official documentation, I saw the “fine-tuning” has the davinci-instruct-beta-v3 model, but when using the API or CLI, it returns an error, indicating that only these four models “ada”, “babbage”, “curie”, and “davinci” can be used. Is it necessary to have a special organization?

github.com

openai/openai-cookbook/blob/main/examples/fine-tuned_qa/olympics-2-create-qa.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<span style=\"color:orange; font-weight:bold\">Note: To answer questions based on text documents, we recommend the procedure in <a href=\"https://github.com/openai/openai-cookbook/blob/main/examples/Question_answering_using_embeddings.ipynb\">Question Answering using Embeddings</a>. Some of the code below may rely on <a href=\"https://github.com/openai/openai-cookbook/tree/main/transition_guides_for_deprecated_API_endpoints\">deprecated API endpoints</a>.</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 2. Creating a synthetic Q&A dataset\n",
    "We use [`davinci-instruct-beta-v3`](https://beta.openai.com/docs/engines/instruct-series-beta), a model specialized in following instructions, to create questions based on the given context. Then we also use [`davinci-instruct-beta-v3`](https://beta.openai.com/docs/engines/instruct-series-beta) to answer those questions, given the same context. \n",
    "\n",
    "This is expensive, and will also take a long time, as we call the davinci engine for each section. You can simply download the final dataset instead.\n",
    "\n",
    "We're using the dataset created using the [previous notebook](olympics-1-collect-data.ipynb)"
   ]

This file has been truncated. show original

What methods can be used to access the davinci-instruct-beta-v3 model mentioned in the article?

sps · April 29, 2023, 4:11pm

The model you specified doesn’t support fine-tuning. In the example you shared, it has been used to create synthetic dataset using the completion endpoint

Topic		Replies	Views
Can we create a private model based on davinci-instruct-beta-v3 using open AI's fine-tuning? API	0	335	April 29, 2023
How to fine tune a model using GPT-3 models? API	1	1332	January 18, 2023
Error when trying to fine tune divinci-003 API	1	746	December 5, 2022
Fine-Tuning the models API	2	818	December 23, 2023
Unable to fine tune on any model besides base models "ada, babbage, curie, davinci" Deprecations fine-tuning , api	3	913	January 25, 2024

Can we create a private model based on davinci-instruct-beta-v3 using open AI's fine-tuning

Related topics