SequentialLearning
/

SuperLinear

mixture-of-experts

Model card Files Files and versions

razmars commited on Apr 27

Commit

4cb4344

·

verified ·

1 Parent(s): 615ec24

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -32,7 +32,7 @@
   "noisy_gating_std_decay": 1,
   "pred_len": 96,
   "seq_len": 512,
-  "top_k_experts": 5,
   "torch_dtype": "float32",
   "transformers_version": "4.40.1",
   "use_fft": 1

   "noisy_gating_std_decay": 1,
   "pred_len": 96,
   "seq_len": 512,
+  "top_k_experts": 1,
   "torch_dtype": "float32",
   "transformers_version": "4.40.1",
   "use_fft": 1