SuperbEmphasis commited on
Commit
bdb1454
·
verified ·
1 Parent(s): e456595

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -5,12 +5,12 @@ base_model:
5
 
6
  Fine tuned with my relatively small (about 3000 samples) sample of roleplay conversations. this datasets RP conversations have 3-15+ turns. this is my $60 attempt to force qwen3 30b to be able to handle RP stuff.
7
 
8
- 3 epochs, 4e-4 learning rate, because screw you qwen3
9
  more info after I can test it.
10
  Q4_K_S gguf incoming soon.
11
 
12
- Reasoning -
13
 
 
14
  here is a cool ST setting that as processed good results.
15
 
16
 
 
5
 
6
  Fine tuned with my relatively small (about 3000 samples) sample of roleplay conversations. this datasets RP conversations have 3-15+ turns. this is my $60 attempt to force qwen3 30b to be able to handle RP stuff.
7
 
8
+ 3 epochs, 4e-4 learning rate, because screw you qwen3...
9
  more info after I can test it.
10
  Q4_K_S gguf incoming soon.
11
 
 
12
 
13
+ Reasoning -
14
  here is a cool ST setting that as processed good results.
15
 
16