aloobun commited on
Commit
9d34981
1 Parent(s): 08b1404

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -16,6 +16,11 @@ tags:
16
  - The original idea was to use this 1.8B model, divide the dataset based on task specific capabilities, train models and transform them into a mixture of experts.
17
  - Hyperparameters: adamw with eps of 1e-8, cosine decay w/ 20% warmup, lr=2e-5.
18
 
 
 
 
 
 
19
  ## Benchamrks:
20
 
21
  WIP
 
16
  - The original idea was to use this 1.8B model, divide the dataset based on task specific capabilities, train models and transform them into a mixture of experts.
17
  - Hyperparameters: adamw with eps of 1e-8, cosine decay w/ 20% warmup, lr=2e-5.
18
 
19
+ ## Format:
20
+ ```
21
+ <|system|></s><|prompt|></s><|answer|>
22
+ ```
23
+
24
  ## Benchamrks:
25
 
26
  WIP