pszemraj commited on
Commit
572f80e
·
1 Parent(s): d7bd96f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -4,7 +4,9 @@ A GPT-2 M 355M parameter model for usage with [ai-msgbot](https://github.com/psz
4
 
5
  This model was fine-tuned on a parsed version of The Wizard of Wikipedia dataset for 10,000 steps. 20/24 layers were frozen for the fine-tuning process.
6
 
7
- ## details
 
 
8
 
9
  `script_speaker_name` = `person alpha`
10
 
 
4
 
5
  This model was fine-tuned on a parsed version of The Wizard of Wikipedia dataset for 10,000 steps. 20/24 layers were frozen for the fine-tuning process.
6
 
7
+ ## conversation data
8
+
9
+ The dataset was tokenized and fed to the model as a conversation between two speakers, whose names are below. this is relevant for writing prompts and filtering/extracting text from responses.
10
 
11
  `script_speaker_name` = `person alpha`
12