Update README.md

README.md

@@ -29,5 +29,7 @@ Below are the results of Vicuna-style testing: 80 questions in various categorie
 | Writing        | 8             | 19                   | 19                 |
 | Total          | 125           | 271                  | 312                |
 
+(A sheet of questions, answers and GPT's reviews are also included in this repo).
 
-Response times are fast: on my GTX 1080ti + Ryzen 3600,it generates between 1.14 tokens/s and 3.77 tokens/s.
+Because of its small size, Eluwa can be used as research into conversational models with older and slower hardware. To load it in a UI like oobabooga, 
+download the model's .bin and .json files, put them in a folder inside the /loras folder, and load it with the OPT 2.7b model.