xformAI commited on
Commit
9e7a1dd
1 Parent(s): 9176d5b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -1,3 +1,8 @@
1
  ---
2
  license: mit
 
 
 
3
  ---
 
 
 
1
  ---
2
  license: mit
3
+ language:
4
+ - en
5
+ library_name: transformers
6
  ---
7
+
8
+ This is a QCQA version of the original model facebook/opt-125m. In this version, the original MHA architecture is preserved but instead of having a single K/V head, different K/V heads corresponding to the same group have the same mean-pooled K or V values. It has upto 6 groups of KV heads per layer instead of original 12 KV heads in the MHA implementation. This implementation is supposed to more efficient than corresponding GQA one. This has been optimized for quality loss.