itsliupeng
/

Mixtral-8x7B-v0.1-top3

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

itsliupeng commited on Dec 18, 2023

Commit

40fb3b9

•

1 Parent(s): 88ed27a

change num_experts_per_tok to 3

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -12,7 +12,7 @@
   "max_position_embeddings": 32768,
   "model_type": "mixtral",
   "num_attention_heads": 32,
-  "num_experts_per_tok": 2,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "num_local_experts": 8,

   "max_position_embeddings": 32768,
   "model_type": "mixtral",
   "num_attention_heads": 32,
+  "num_experts_per_tok": 3,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "num_local_experts": 8,