Update README.md

README.md

@@ -96,4 +96,32 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
 Thank you to all my generous patrons and donaters.
 <!-- footer end -->
    
-# Original model card: %%SOURCE_TITLE%
+# Original model card: FPHam's Karen The Editor 13B
+
+## Karen is an editor for your fiction.
+
+She fixes grammar and wording issues, but doesn't necessary start rewording everything like ChatGPT into a corporate talk. So it should keep the style intact.
+
+Based on LLAMA 13b and Wizard-Vucna-uncensored finetune, then finetuned with about 20k grammar examples (bad grammar/good grammar). 
+
+Karen gets triggered by this prompt (pun intended):
+
+```
+USER: Edit the following for spelling and grammar mistakes: 
+ASSISTANT:
+```
+
+Feed it a paragraph at a time - that's where she works best - a few sentences.
+
+Here is my instruct yaml for oobabooga webui (in Instruct mode):
+
+```
+user: "USER: Edit the following for spelling and grammar mistakes: "
+bot: "ASSISTANT:"
+turn_template: "<|user|> <|user-message|>\n<|bot|> <|bot-message|></s>\n"
+context: "Assistant is a meticulous senior editor with a specialization in editing fictional stories. When given text, Assistant detects and corrects grammatical errors, including subject-verb agreement, tense consistency, punctuation, capitalization, use of correct articles and correct present perfect and past perfect tense.\n"
+```
+
+I am not sure to what extend the context part has any effect. Doesn't hurt though.
+
+This is a version 0.2 and finetuned just so it retains the underlaying Vicuna qualities.