Update README.md

README.md

@@ -29,7 +29,7 @@ Disappointed with some quirks of my previous kitchen sink merges (like token/ins
 
 - [DrNicefellow/migtissera/Tess-M-Creative-v1.0](https://huggingface.co/migtissera/Tess-M-Creative-v1.0) and [NousResearch/Nous-Capybara-34B](https://huggingface.co/NousResearch/Nous-Capybara-34B) are both "undertrained" Yi models. I find they excel at raw completion performance (like long novel continuations) while still retaining some Vicuna instruct ability. This may be why some still prefer the original Tess 1.0/Capybara merge.
 
-I consider this a more "focused" merge and a possible base for a storytelling finetune/LASER in the future, once I bite the bullet and rent some A100s or a MI300. I will investigate other models (perhaps chatML models?) for a more "factual assistant" focused merge, as well as a coding-focused merge if I can't find one to suit my needs.
+I consider this a more "focused" merge that previous ones. I will investigate other models (perhaps chatML models?) for a more "factual assistant" focused merge, as well as a coding-focused merge if I can't find one to suit my needs.
 
 
 ## Prompt template: Orca-Vicuna
@@ -60,6 +60,8 @@ To load/train this in full-context backends like transformers, you *must* change
 
 See: https://huggingface.co/brucethemoose/Yi-34B-200K-DARE-megamerge-v8#testing-notes
 
+Thiss is a possible base for a storytelling finetune/LASER in the future, once I bite the bullet and rent some A100s or a MI300. 
+
 I have tested this merge with with novel-style continuation (but not much chat-style roleplay), and some assistant-style responses and long context analysis. I haven't seen any refusals so far.
 
 ## Merge Details