Aeala commited on
Commit
96bd8fc
1 Parent(s): a227315

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +27 -0
README.md ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets:
3
+ - gozfarb/ShareGPT_Vicuna_unfiltered
4
+ ---
5
+
6
+ ## LoRA Info:
7
+ Please note that this is a highly experimental LoRA model. It may do some good stuff, it might do some undesirable stuff. Training is basically done now. Feel free to try it!~
8
+
9
+ **Important Note**: While this is trained on a cleaned ShareGPT dataset like Vicuna used, this was trained in the *Alpaca* format, so prompting should be something like:
10
+
11
+ ```
12
+ ### Instruction:
13
+
14
+ <prompt> (without the <>)
15
+
16
+ ### Response:
17
+ ```
18
+
19
+ Current upload: checkpoint of step 400 in training.
20
+
21
+
22
+ ## Benchmarks
23
+ **wikitext2:** Coming soon...
24
+
25
+ **ptb-new:** Coming soon...
26
+
27
+ **c4-new:** Coming soon...