jukofyork commited on
Commit
4ef7d65
1 Parent(s): 503aef7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -106,7 +106,7 @@ So instead of having just a single vector that we add (and in essence adding a b
106
 
107
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65995c45539c808e84c38bf1/vZ2Gys3huKAWIVe0wz2-q.png)
108
 
109
- but where `lora_A` looks at the ***input*** to the transformation; instead of the ***output*** of the (`down_proj`) transformation like these new (non-orthogonal) "multiplicative-LoRAs":
110
 
111
  ---
112
 
 
106
 
107
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65995c45539c808e84c38bf1/vZ2Gys3huKAWIVe0wz2-q.png)
108
 
109
+ but where `lora_A` looks at the ***input*** to the transformation; instead of the ***output*** of the (`down_proj`) transformation like these new (non-orthogonal) "multiplicative-LoRAs"...
110
 
111
  ---
112