Vinsingh commited on
Commit
ab0f32a
1 Parent(s): 2fd1376

Upload README (1).md

Browse files
Files changed (1) hide show
  1. README (1).md +15 -0
README (1).md ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - hi
5
+ - en
6
+ ---
7
+
8
+ This is the pytorch model parameters and associated data used for training a small transformer model from scratch.
9
+ The transformer model is used to train for translation from hindi_latin to english.
10
+
11
+ Among the files, training dataset used to create the model is also there. Data used for training is semi-synthetic.
12
+
13
+ Steps for creating datasets:
14
+ Obtain actualuser questions in hindi and human translations thereof in english.
15
+ Prompt GPT to create variations of key words taking phonetics in account and giving a user persona.