Skip to content

README.md

Latest commit

 

History

History
4 lines (4 loc) · 441 Bytes

README.md

File metadata and controls

4 lines (4 loc) · 441 Bytes

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".