Generate the WizardCoder Instruct from the CodeAlpaca
Python 100.00%
wizardcoder_instruct_generator's Introduction
WizardCoder_Instruct_Generator
You need to write the completeion function by openAI api, which recieves the prompt and output the GPT4 response.
The final output is saved in new_code_demo.json.
I give a demo in new_code_demo.json, you need to rerun 3-4 times of generate_evloveinstruct.py to generate the instructs, fine-tune your model and find the best performance on Human-eval, which is the same as the paper "Wizarder-Coder".
Thanks for this repo! I am also reading the paper recently, but I did not notice which LLM the WizardCoder used to generated their Evol-Instruct data. According to your implementation, gpt4_azure is used, is it the same with WizardCoder (considering that Microsoft insiders could use the API for free since early this year), or you just guess they used GPT-4?