Update README.md

README.md

@@ -20,6 +20,15 @@ W_{mistral} + LoRA_{hermes} = W_{hermes} \\
 W_{hermes} - LoRA_{hermes} = W_{mistral}
 $$
 
+
+### Why Though?
+unfortunately this is not as simple as [typeof/zephyr-7b-beta-lora](https://huggingface.co/typeof/zephyr-7b-beta-lora) 
+due to the way in which [OpenHermes](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) was trained... 
+by adding tokens, the corresponance is not 1-to-1 with [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
+as is the case with [typeof/zephyr-7b-beta-lora](https://huggingface.co/typeof/zephyr-7b-beta-lora) ... 
+nevertheless, if you have found yourself here, I'm sure you can figure out how to use it... if not, open up an issue!
+
+
 <!--
 $$ W_{mistral} + LoRA_{zephyr} = W_{zephyr} $$
 ```