pa4 more edits

Author: ricj

_pages/dat450/assignment4.md

@@ -1,13 +1,13 @@
 ---
 layout: page
-title: 'DAT450/DIT247: Programming Assignment 4: Supervised Fine-Tuning (SFT) a Small LLM with LoRA'
+title: 'DAT450/DIT247: Programming Assignment 4: Supervised Fine-Tuning (SFT) with LoRA'
 permalink: /courses/dat450/assignment4/
 description:
 nav: false
 nav_order: 4
 ---
 
-# DAT450/DIT247: Programming Assignment 4: Supervised Fine-Tuning (SFT) a Small LLM with LoRA
+# DAT450/DIT247: Programming Assignment 4: Supervised Fine-Tuning (SFT) with LoRA
 
 In this assignment, you will perform supervised fine-tuning (SFT) of a small open LLM (preferably [OLMo-2 1B](https://huggingface.co/allenai/OLMo-2-0425-1B)) on [Alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca), a dataset of 52k instructions generated by OpenAI's text-davinci-003 engine. You will convert this dataset into instruction-response pairs, fine-tune a causal language model using LoRA (Low-Rank Adaptation), and evaluate it through prompted inference and comparison with other methods.