Update README.md

README.md

@@ -15,8 +15,7 @@ tags:
 
 This is a Parameter Efficient Fine Tuning (PEFT) Low Rank Adaptation (LoRA) of 
 the [esm2_t6_8M_UR50D](https://huggingface.co/facebook/esm2_t6_8M_UR50D) model for the (binary) token classification task of 
-predicting RNA binding sites of proteins. The Github with the training script and conda env YAML can be
-[found here](https://github.com/Amelie-Schreiber/esm2_LoRA_binding_sites/tree/main). You can also find a version of this model 
+predicting RNA binding sites of proteins. You can also find a version of this model 
 that was fine-tuned without LoRA [here](https://huggingface.co/AmelieSchreiber/esm2_t6_8M_UR50D_rna_binding_site_predictor). 
 
 ## Training procedure
@@ -25,7 +24,10 @@ This is a Low Rank Adaptation (LoRA) of `esm2_t6_8M_UR50D`,
 trained on `166` protein sequences in the [RNA binding sites dataset](https://huggingface.co/datasets/AmelieSchreiber/data_of_protein-rna_binding_sites)
 using a `80/20` train/test split. This model was trained with class weighting due to the imbalanced nature 
 of the RNA binding site dataset (fewer binding sites than non-binding sites). You can train your own version 
-using [this notebook](https://huggingface.co/AmelieSchreiber/esm2_t6_8M_weighted_lora_rna_binding/blob/main/LoRA_binding_sites_no_sweeps_v2.ipynb)!
+using [this notebook](https://huggingface.co/AmelieSchreiber/esm2_t6_8M_weighted_lora_rna_binding/blob/main/LoRA_binding_sites_no_sweeps_v2.ipynb)! 
+You just need the RNA `binding_sites.xml` file [found here](https://huggingface.co/datasets/AmelieSchreiber/data_of_protein-rna_binding_sites). 
+A similar model can also be trained using the Github with a training script and conda env YAML, which can be
+[found here](https://github.com/Amelie-Schreiber/esm2_LoRA_binding_sites/tree/main). This version uses wandb sweeps for hyperparameter search. 
 
 ```
 {'eval_loss': 0.49476009607315063,