Fine-Tuning-LLMs-for-Medical-Entity-Extraction

(★ 91)

Exploring the potential of fine-tuning Large Language Models (LLMs) like Llama2 and StableLM for medical entity extraction. This project focuses on adapting these models using PEFT, Adapter V2, and LoRA techniques to efficiently and accurately extract drug names and adverse side-effects from pharmaceutical texts

File Explorer

Download Latest Version (.zip)

- - entity-extraction-data.json
  - entity-extraction-test-data.json
  - entity-extraction-train-data.json
  - test.pt
  - train.pt
- - Abilify.txt
  - Advair.txt
  - Ambien.txt
  - Amlodipine.txt
  - AndroGel.txt
  - Aranesp.txt
  - Atorvastatin.txt
  - Atripla.txt
  - Byetta.txt
  - Celexa.txt
  - Cialis.txt
  - Complera.txt
  - Crestor.txt
  - Cymbalta.txt
  - Doxycycline.txt
  - Enbrel.txt
  - Epogen.txt
  - Etanercept.txt
  - Humira.txt
  - infliximab.txt
  - Januvia.txt
  - Levitra.txt
  - Lexapro.txt
  - Lipitor.txt
  - Lisinopril.txt
  - Lunesta.txt
  - Metoprolol.txt
  - Neulasta.txt
  - Neupogen.txt
  - Nexium.txt
  - Nuvigil.txt
  - Onglyza.txt
  - Prevacid.txt
  - Prezista.txt
  - Prilosec.txt
  - Protonix.txt
  - Provigil.txt
  - Prozac.txt
  - Remicade.txt
  - Rituxan.txt
  - rituximab.txt
  - Singulair.txt
  - Spiriva.txt
  - Staxyn.txt
  - Symbicort.txt
  - Viagra.txt
  - Victoza.txt
  - Vytorin.txt
  - Zocor.txt
  - Zoloft.txt
- - abilify.txt
  - Advair.txt
  - Ambien.txt
  - Amlodipine.txt
  - AndroGel.txt
  - Aranesp.txt
  - Atorvastatin.txt
  - Atripla.txt
  - Byetta.txt
  - Celexa.txt
  - Cialis.txt
  - Complera.txt
  - Crestor.txt
  - Cymbalta.txt
  - Doxycycline.txt
  - Enbrel.txt
  - Epogen.txt
  - etanercept.txt
  - Humira.txt
  - infliximab.txt
  - Januvia.txt
  - Levitra.txt
  - Lexapro.txt
  - Lipitor.txt
  - Lisinopril.txt
  - Lunesta.txt
  - Metoprolol.txt
  - Neulasta.txt
  - Neupogen.txt
  - Nexium.txt
  - Nuvigil.txt
  - Onglyza.txt
  - Prevacid.txt
  - Prezista.txt
  - Prilosec.txt
  - Protonix.txt
  - Provigil.txt
  - Prozac.txt
  - Remicade.txt
  - Rituxan.txt
  - rituximab.txt
  - Singulair.txt
  - Spiriva.txt
  - Staxyn.txt
  - Symbicort.txt
  - Viagra.txt
  - Victoza.txt
  - Vytorin.txt
  - Zocor.txt
  - Zoloft.txt
- predictions-llama2-adapter.json
- predictions-llama2-lora.json
- predictions-stablelm-adapter.json
- predictions-stablelm-lora.json
- prompt-template.txt
- adapter_v2.py
- lora.py
- __init__.py
- base.py
- inference_adapter.py
- inference_base.py
- inference_lora.py
- __init__.py
- adapter.py
- adapter_v2.py
- config.py
- lora.py
- model.py
- packed_dataset.py
- rmsnorm.py
- tokenizer.py
- utils.py
- data-prepare.ipynb
- evaluate.ipynb
- inference_adapter.ipynb
- inference_base.ipynb
- inference_lora.ipynb
- combine-data.py
- convert_hf_checkpoint.py
- data-prepare.py
- download.py
- evaluate.py
- prepare_entity_extraction_data.py
- scrape_drugs_data.py
.gitignore
env.example
LICENSE.txt
README.md
requirements.txt

# Installation Guide

1. Get the code

git clone https://github.com/architkaila/Fine-Tuning-LLMs-for-Medical-Entity-Extraction

Downloads the entire project code from GitHub to your computer.

cd Fine-Tuning-LLMs-for-Medical-Entity-Extraction

Moves into the project folder you just downloaded.

2. Python

Easy Recommended

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

pip install -r requirements.txt

Installs the Python libraries listed in requirements.txt (or similar).

✅ If it runs without errors and prints output in the terminal, it worked.

Pulled directly from this repo's README.