Fine-Tuning GPT3 for free

!pip install openai

import openaiimport pandas as pdimport stringopenai.api_key = 'YOUR API KEY'

df = pd.read_csv('jokes.csv')df.head()

{"prompt": "<text>", "completion": "<text to be generated>"}
{"prompt": "<text>", "completion": "<text to be generated>"}
{"prompt": "<text>", "completion": "<text to be generated>"}

1. 準備微調數據集
   但是，OpenAI 具有將 CSV、TSV、XLSX 和 JSON 轉換為 JSONL 文件的功能。 我已經預處理了數據集。 現在讓我們將其轉換為 jsonl 格式。

!yes | openai tools fine_tunes.prepare_data -f 'joke.csv'

#write your file name instead of jokes_prepared.jsonl
with open("joke_prepared.jsonl") as f:
      response = openai.File.create(file=f, purpose='fine-tune')
print(response)

response = openai.FineTune.create(training_file="YOUR FILE ID", model='ada')

response = openai.FineTune.retrieve(id="YOUR FINE-TUNE ID")

# ft_model should have your model id
ft_model = "ada:ft-personal-2022-07-22-11-25-19"
res = openai.Completion.create(model=ft_model, prompt="I hate ... ", max_tokens=18, temperature=1)