Safetensors
English
bert_hash
custom_code
davidmezzetti commited on
Commit
7afc068
·
verified ·
1 Parent(s): 7dd49e2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -93,3 +93,8 @@ This model demonstrates that smaller models can still be productive models.
93
  The hope is that this work opens the door to many in building small encoder models that pack a punch. Models can be trained in a matter of hours using consumer GPUs.
94
 
95
  Imagine more specialized models like this for medical, legal, science and more.
 
 
 
 
 
 
93
  The hope is that this work opens the door to many in building small encoder models that pack a punch. Models can be trained in a matter of hours using consumer GPUs.
94
 
95
  Imagine more specialized models like this for medical, legal, science and more.
96
+
97
+
98
+ ## More Information
99
+
100
+ Read more about this model and how it was built in [this article](https://medium.com/neuml/training-tiny-language-models-with-token-hashing-b744aa7eb931).