AmelieSchreiber commited on
Commit
45e45d6
1 Parent(s): c20ef98

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -10,7 +10,16 @@ tags:
10
  - biology
11
  ---
12
 
 
 
13
  These are the checkpoints for the first ever QLoRA for ESM-2! They haven't been checked for overfitting yet, so use with caution!
14
  You can load and use them similarly to the LoRA models. This is the smallest `esm2_t6_8M_UR50D` model, so the metrics aren't great.
15
  Scaling to larger models for better metrics is in progress.
16
 
 
 
 
 
 
 
 
 
10
  - biology
11
  ---
12
 
13
+ # ESM-2 QLoRA
14
+
15
  These are the checkpoints for the first ever QLoRA for ESM-2! They haven't been checked for overfitting yet, so use with caution!
16
  You can load and use them similarly to the LoRA models. This is the smallest `esm2_t6_8M_UR50D` model, so the metrics aren't great.
17
  Scaling to larger models for better metrics is in progress.
18
 
19
+ ## QLoRA Info
20
+
21
+ Note, we are only training 0.58% of the parameters, using only the query, key, and value weight matrices.
22
+
23
+ ```
24
+ trainable params: 23682 || all params: 4075265 || trainable%: 0.5811155838945443
25
+ ```