Isaak-Carter
/

SmalJ.O.S.I.E.-48x101M-Chat

Text Generation

Mixture of Experts

Felladrin/Smol-Llama-101M-Chat-v1

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Isaak-Carter commited on Mar 20

Commit

ae9196b

•

1 Parent(s): 67299ca

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -14,7 +14,7 @@
   "max_position_embeddings": 1024,
   "model_type": "mixtral",
   "num_attention_heads": 24,
-  "num_experts_per_tok": 2,
   "num_hidden_layers": 6,
   "num_key_value_heads": 8,
   "num_local_experts": 48,

   "max_position_embeddings": 1024,
   "model_type": "mixtral",
   "num_attention_heads": 24,
+  "num_experts_per_tok": 8,
   "num_hidden_layers": 6,
   "num_key_value_heads": 8,
   "num_local_experts": 48,