Thanks to visit codestin.com
Credit goes to github.com

Skip to content

JiaxingQiu/llm_topic_extraction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

31 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

data

inputs

  • "./data/answer_df_raw.csv" contains 77175 social media posts.
  • "./data/fea_df.csv" contains topical features to be queried by LLM.

outputs

  • create subfolder "llama_data" and "gpt_data" locally.
  • llama extracted topics should be stored as "./llama_data/answer_df.csv"
  • GPT4 extracted topics should be stored as "./gpt_data/answer_df.csv"

script

  • llama_inference_3.1.ipynb and llama_inference.py are main scripts generating topic labels.
  • demo_gpt_inference.ipynb is the pseudo code for GPT4 qeuries, containing necessary function (e.g. format_prompt)

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •