Sao10K commited on
Commit
3623907
·
verified ·
1 Parent(s): 714453e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -19,9 +19,8 @@ Make sure to adapt your cards to a group-chat friendly style?
19
  Training Details:
20
  ```
21
  - Uses L3-Instruct Format.
22
- - One designated user per entry is the GPT-turn, while all other characters are different, assigned Human-turns, if not Axolotl does a fit.
23
- # I am experimenting with doing the opposite too, having all but 1 be GPT-turns.
24
- - Unique Characters per entry vary from 2-5 Characters usually.
25
  - There is roughly only ~3K sample entries.
26
  - May not be the smartest due to all samples being roleplay / conversational data.
27
  ```
 
19
  Training Details:
20
  ```
21
  - Uses L3-Instruct Format.
22
+ - One designated character per entry is the Human-turn, while all other characters are different, assigned GPT-turns, not in order to simulate real group chats.
23
+ - Per entry, it varies from 2-5 Unique Characters usually.
 
24
  - There is roughly only ~3K sample entries.
25
  - May not be the smartest due to all samples being roleplay / conversational data.
26
  ```