Update README.md

README.md

@@ -1,9 +1,14 @@
 ---
 library_name: peft
 ---
+
+# ESM-2 LoRA for CAFA-5 Protein Function Prediction
+This is a Low Rank Adaptation (LoRA) of [cafa_5_protein_function_prediction](https://huggingface.co/AmelieSchreiber/cafa_5_protein_function_prediction), 
+which is a fine-tuned (without LoRA) version of `facebook/esm2_t6_8M_UR50D`, for the same task. 
+
 ## Training procedure
  Using Hugging Face's Parameter Efficient Fine-Tuning (PEFT) library, a Low Rank Adaptation was trained for 
- 3 epochs on the CAFA-5 protein sequences dataset at an 80/20 train/test split on. The dataset can be 
+ 3 epochs on the CAFA-5 protein sequences dataset at an 80/20 train/test split. The dataset can be 
  [found here](https://huggingface.co/datasets/AmelieSchreiber/cafa_5). Somewhat naively, the model was trained on
  the `train_sequences.fasta` file of protein sequences, with the `train_terms.tsv` file serving as the labels. 
  The gene ontology used is a hierarchy, and so the labels lower in the hierchay should be weighted more, or the 
@@ -20,6 +25,8 @@ Validation Micro Recall: 0.2911,
 Validation Macro Recall: 0.9968
 ```
 
+Future iterations of this model will need to take into account class weighting. 
+
 ### Framework versions
 
 - PEFT 0.4.0