PhysiQuanty commited on
Commit
84b8ae3
·
verified ·
1 Parent(s): 580b7d5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -25,6 +25,12 @@ This repo uses `trust_remote_code=True` because it ships a custom `modeling_*.py
25
 
26
  (In French only, we plan 20 languages as well as scientific and mathematical knowledge for BinaryLLM1)
27
 
 
 
 
 
 
 
28
  ## Load (Python)
29
 
30
  ```python
 
25
 
26
  (In French only, we plan 20 languages as well as scientific and mathematical knowledge for BinaryLLM1)
27
 
28
+ - 10 millions params
29
+ - 2 billions training tokens
30
+ - 40k steps
31
+ - 1e-4 learning rate
32
+ - Fp32 weight, FSDP training on 8 NVIDIA V100
33
+
34
  ## Load (Python)
35
 
36
  ```python