deepseek-ai
/

DeepSeek-V4-Pro-Base

Model card Files Files and versions

GeeeekExplorer commited on 13 days ago

Commit

2fd8117

·

verified ·

1 Parent(s): f95170c

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -14,7 +14,7 @@
   "hidden_size": 7168,
   "index_head_dim": 128,
   "index_n_heads": 64,
-  "index_topk": 512,
   "initializer_range": 0.02,
   "max_position_embeddings": 1048576,
   "model_type": "deepseek_v4",

   "hidden_size": 7168,
   "index_head_dim": 128,
   "index_n_heads": 64,
+  "index_topk": 1024,
   "initializer_range": 0.02,
   "max_position_embeddings": 1048576,
   "model_type": "deepseek_v4",