Update README.md

Files changed (1) hide show

README.md CHANGED Viewed

	@@ -10,3 +10,6 @@ We have built an educational assistant using Flan-T5 large, a modestly sized lan
10
11	Model quantization results in a 68% reduction in memory footprint without severely impacting performance, maintaining a 32% accuracy. Furthermore, our flagship model, T5utor, utilizing RAG, increased performance by 4.4% compared to our Multiple Choice Question Answering (MCQA) model. After our training pipelines, some of the models achieve higher accuracies on common benchmarks relative to the reference model.
12

 Model quantization results in a 68% reduction in memory footprint without severely impacting performance, maintaining a 32% accuracy. Furthermore, our flagship model, T5utor, utilizing RAG, increased performance by 4.4% compared to our Multiple Choice Question Answering (MCQA) model. After our training pipelines, some of the models achieve higher accuracies on common benchmarks relative to the reference model.
+## Approach
+![Approach Diagram](/approach.png)
+*Figure 1: Diagram showing our general approach. Starting from the left with our chosen generator model LaMini-Flan-T5-783M, then going through multiple fine-tuning stages. The names of the models follow the nomenclature in Table 1. The relative sizes of the datasets are also significant, with the DPO External Dataset being roughly six times the size of the other smaller datasets.*