Update README.md

README.md

@@ -12,18 +12,17 @@ library_name: adapter-transformers
 
 I was just curious to see if something special might happen if one uses:
 $$
-\text{{Evangelion}} = \text{{high-quality DPO dataset}} + \text{{merge of DPO optimized model and non-DPO optimized model}}
+\text{{Evangelion}} = \text{{high-quality DPO dataset}} + \text{{merge of DPO optimized and non-DPO optimized model}}
 $$
 
-The underlying model that I used was `/Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp`.
-
-
+The underlying model that I used was `/Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp`.  
+**Disclaimer:** I'm by no means a pro; therefore, no guarantee. I just wanted to put a cool anime picture on my model card.
 
 
 # Dataset
 Dataset: `/argilla/distilabel-intel-orca-dpo-pairs`
 
-The dataset was quality over quantity roughly ~3000 samples but they were high quality (aqccording to the chosen_score).
+The dataset was quality over quantity roughly ~3000 samples but they were high quality (aqccording to the chosen_score).  
 The following filters were applied to the original dataset:
 ```python
 dataset = dataset.filter(
@@ -35,7 +34,8 @@ dataset = dataset.filter(
 ```
 
 # Chat Template
-I decided to go with the ChatML template which I also integrated into this models tokenizer.
+I decided to go with the ChatML which is used for OpenHermes2.5
+By the way I integreated the chat template into the models tokenizer.
 ```
 <|im_start|>system
 {system}<|im_end|>