Update README.md

README.md

@@ -34,9 +34,9 @@ Healed Llama-3 15B Frankenmerge
 
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64f74b6e6389380c77562762/MCdGdalCCtOVPn8X7rqha.jpeg)
 
-This is the third iteration "Emerald" of the final four and the one I liked the most. It has had limited testing though, but seems decent.
+This is the third iteration "Emerald" of the final four and the one I liked the most. It has had limited testing though, but seems relatively decent.
 
-Findings: o_proj and down_proj can be stolen from Aethora-v2 so new 15B frankenmerges don't seem to need finetuning to "heal" the layers at all.
+Findings: o_proj and down_proj can be stolen from Aethora-v2 so new 15B frankenmerges don't seem to really ***need*** finetuning to "heal" the layers at all.
 
 # <h1>merge</h1>
 
@@ -45,7 +45,7 @@ This is a merge of pre-trained language models created using [mergekit](https://
 # <h1>Merge Details</h1>
 # <h1>Merge Method</h1>
 
-This model was merged using an iterative merging process. (Probably ~15 models got thrown away in the process.)
+This model was merged using an iterative merging process. (Probably ~10 models got thrown away in the process.)
 
 # <h1>Models Merged</h1>