Update README.md

clarification on ongoing repairs

README.md

@@ -15,7 +15,7 @@ base_model: mistralai/Mistral-Small-24B-Base-2501
 ---
 # DeepHermes 3 - Mistral 24B Preview (text only varient)
 
-Derivative of NousResearch / DeepHermes-3-Mistral-24B-Preview.  
+Derivative of [NousResearch/DeepHermes-3-Mistral-24B-Preview](https://huggingface.co/NousResearch/DeepHermes-3-Mistral-24B-Preview).  
 All `[TOOL_*]` tokens removed from `special_tokens_map.json`; architecture unchanged.  
 Pure-text chat model intended for merges and creative work. 
 
@@ -30,8 +30,8 @@ But WHY?
 
 Cuz. I'm trying to merge this fabulous little trickster with RP models AND IT WON'T PLAY NICE. 
 I have to pad their tokenizers, AND I have to disable this ickle goblin's 👹📞☎️ constant attempts to call out. 
-We'll get there. Hopefully, the padding and taking out the tool calling will stop it from looping things like:
-"I am goblin, I am your pet, I am your slave, I am your little bitch, I am your chair, I am..."
+We'll get there. Hopefully, padding the tozenizers of the models I merge it with, and taking out the tool calling will stop merges from looping things like:
+"I am goblin, I am your pet, I am your slave, I am your little bitch, I am your chair, I am goblin, I am..."
 Yes, yes darling... *eye roll* 
 
 I've heard *that* one before, and not from AI...