PhilipQuirke commited on
Commit
12e3bd8
·
1 Parent(s): b1a94f5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -3
README.md CHANGED
@@ -4,13 +4,11 @@ license: apache-2.0
4
 
5
  Contains file for Transformer model that answers 5-digit addition questions (e.g. 12345+67890=) with near zero low loss.
6
  Model has answered 1 million addition questions with any errors.
7
- Model has 2 layers, 3 attention heads, d-model = 510, d-head = 170, and was trained for 30K epochs.
8
 
 
9
  The CoLab used to train the model is here:
10
  https://github.com/PhilipQuirke/transformer-maths/blob/main/assets/Accurate_Addition_Train.ipynb
11
 
12
  The CoLab used to analyse the model is here:
13
  https://github.com/PhilipQuirke/transformer-maths/blob/main/assets/Accurate_Addition_Analyse.ipynb
14
 
15
-
16
-
 
4
 
5
  Contains file for Transformer model that answers 5-digit addition questions (e.g. 12345+67890=) with near zero low loss.
6
  Model has answered 1 million addition questions with any errors.
 
7
 
8
+ Model has 2 layers, 3 attention heads, d-model = 510, d-head = 170, and was trained for 30K epochs.
9
  The CoLab used to train the model is here:
10
  https://github.com/PhilipQuirke/transformer-maths/blob/main/assets/Accurate_Addition_Train.ipynb
11
 
12
  The CoLab used to analyse the model is here:
13
  https://github.com/PhilipQuirke/transformer-maths/blob/main/assets/Accurate_Addition_Analyse.ipynb
14