kst23 commited on
Commit
a95f5e3
1 Parent(s): 642ecde

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -27,7 +27,7 @@ This is the very first version of CAC (0.1) and is still under development. For
27
 
28
  - The dataset was generated manually and is internal to CodeMate.
29
 
30
- - Training Techniques: The model was fine-tuned using Flash Attention 2, trained over 15 hours on 40 A100-80GB GPUs.
31
 
32
  - A sequence length of 8096 tokens was used during training.
33
 
 
27
 
28
  - The dataset was generated manually and is internal to CodeMate.
29
 
30
+ - Training Techniques: The model was fine-tuned using Flash Attention 2.
31
 
32
  - A sequence length of 8096 tokens was used during training.
33