qf

README.md

@@ -19,8 +19,9 @@ license: llama2
 # Shining Valiant
 
 Shining Valiant is a chat model built on the Llama 2 architecture, finetuned on our data for insight, creativity, passion, and friendship.
-
-(70b parameters, safetensors format)
+ - Uses the llama-2-70b-chat architecture and safetensors
+ - Finetuned on multiple runs across private and public data
+ - Data focused on knowledge, enthusiasm, and structured reasoning
 
 ## Prompting:
 Shining Valiant uses the same prompt format as Llama 2 Chat - feel free to use your existing prompts and scripts!
@@ -41,7 +42,7 @@ Our dataset is:
 75% - our custom AI instruction-tuned dataset, created and curated for increased general capability, insight, logic, depth, and specific personality
 
 
-25% - a selection of open-source AI data from a variety of datasets to supplement general knowledge and reasoning
+25% - a selection of open-source AI data from a variety of datasets to supplement general knowledge and reasoning, pruned through randomization and automated quality ranking