allenai
/

OLMoE-1B-7B-0924

Text Generation

Mixture of Experts

Inference Endpoints

Model card Files Files and versions Community

awettig commited on 21 days ago

Commit

83792c6

•

1 Parent(s): 4e1dee5

Fix load balancing coefficient

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -22,7 +22,7 @@
   "pad_token_id": 1,
   "rope_scaling": null,
   "rope_theta": 10000.0,
-  "router_aux_loss_coef": 0.001,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.43.0.dev0",

   "pad_token_id": 1,
   "rope_scaling": null,
   "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.01,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.43.0.dev0",