stepfun-ai
/

Step-3.5-Flash-Base-Midtrain

Text Generation

Model card Files Files and versions

Tingdan commited on Mar 9

Commit

c0ca721

·

verified ·

1 Parent(s): f66eedf

Update config.json

Files changed (1) hide show

config.json +1 -0

config.json CHANGED Viewed

@@ -31,6 +31,7 @@
   "moe_router_activation": "sigmoid",
   "moe_router_scaling_factor": 3.0,
   "att_impl_type": "GQA",
   "rope_theta": [
     5000000.0,
     10000.0,

   "moe_router_activation": "sigmoid",
   "moe_router_scaling_factor": 3.0,
   "att_impl_type": "GQA",
+  "tie_word_embeddings": false,
   "rope_theta": [
     5000000.0,
     10000.0,