sft miagkyi

## 10k_reports_to_tweets.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              6 stars
            
          
                miagkyi
                / 10k_reports_to_tweets.md
            
            
              Created
              October 17, 2023 17:34
            
          
    Fine-tuning llama 2 7B to analyze financial reports and write “funny” tweets
Sharing some insights from a recent weekend fun project where I tried to analyze and summarize financial reports using a fine-tuned LLM.
My initial goal was to train a model to summarize the annual/quarterly financial reports of public companies (aka 10-K / 10-Q). But, realizing that straightforward financial summaries are boring, I thought of tuning LLM to generate sarcastic summaries of these reports. Something short I could post on Twitter.
Data exploration and dataset prep
Working with financial reports ain’t easy. You download them in html format, they’re pretty dense with ~100 pages filled with tables that can be tough to parse, many legal disclaimers and various useless info. I knew I wanted to get 3-5 funny tweets as an output from a report. But I spent quite some time figuring out what data to actually input to get the result - a page, a section, a table?

  
## 10k_reports_to_tweets.py
from datetime import datetime, timedelta
import concurrent.futures
import csv
import html
import os
import time

from bs4 import BeautifulSoup
from dotenv import load_dotenv
import nltk
	from datetime import datetime, timedelta
	import concurrent.futures
	import csv
	import html
	import os
	import time

	from bs4 import BeautifulSoup
	from dotenv import load_dotenv
	import nltk