mhla commited on
Commit
346dddf
·
verified ·
1 Parent(s): b512feb

Add note on generation parameters

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -39,6 +39,10 @@ Custom GPT with RoPE, QK-norm, ReLU² activation, value embeddings (ResFormer),
39
  | Vocab size | 32,768 (BPE, GPT-4 style split pattern) |
40
 
41
 
 
 
 
 
42
  ## Quick Start
43
 
44
  ```python
 
39
  | Vocab size | 32,768 (BPE, GPT-4 style split pattern) |
40
 
41
 
42
+ ## Notes
43
+
44
+ **Generation parameters:** You may need to play with temperature to get good results. The default is `0.6` with `top_k=50`.
45
+
46
  ## Quick Start
47
 
48
  ```python