horiz94 commited on
Commit
dacf94a
1 Parent(s): 7b9c234

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -104,7 +104,7 @@ FLM-101B is trained on a cluster of 24 DGX-A800 GPU (8×80G) servers for less th
104
 
105
  #### Software
106
 
107
- FLM-101B was trained with Megatron-FLM(open source soon...) which is modified based on Megatron-LM.
108
  It uses a 3D(DP+TP+PP) parallelism approach and distributed optimizer.
109
 
110
 
 
104
 
105
  #### Software
106
 
107
+ FLM-101B was trained with a codebase adapted from Megatron-LM.
108
  It uses a 3D(DP+TP+PP) parallelism approach and distributed optimizer.
109
 
110