Update README.md

README.md

@@ -19,7 +19,7 @@ The dataset consists of 2800 samples, with the composition as follows:
 These samples were then back-filled using gpt-4/gpt-3.5-turbo-16k or otherwise converted to fit the prompt format.
 
 ## Prompt Format
-The model was finetuned with a prompt format similar to the original SuperHOT prototype:
+The model uses the following prompt format:
 ```
 ---
 style: roleplay
@@ -54,12 +54,4 @@ Human: In your next reply, write at least two paragraphs. Be descriptive and imm
 [System note: Write at least two paragraphs. Be descriptive and immersive, providing vivid details about {{char}}'s actions, emotions, and the environment.]
 {{char}}:
 ```
-The third one seems to work the best. I would recommend experimenting with creating your own to best suit your needs.
-
-## Finetuing Parameters
-- LoRA Rank: 64
-- LoRA Alpha: 16
-- LoRA Dropout: 0.1
-- BF16 Training
-- Cutoff Length: 2048
-- Training Epoch(s): 2
+The third one seems to work the best. I would recommend experimenting with creating your own to best suit your needs.