gabrielmbmb
/

Upcycled-Qwen1.5-MoE2.7B

Text Generation

Inference Endpoints

Model card Files Files and versions Community

gabrielmbmb HF staff commited on Mar 29, 2024

Commit

8761fe4

·

verified ·

1 Parent(s): 607043e

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -14,7 +14,7 @@
   "max_position_embeddings": 32768,
   "max_window_layers": 21,
   "model_type": "qwen2_moe",
-  "moe_intermediate_size": 1408,
   "norm_topk_prob": false,
   "num_attention_heads": 16,
   "num_experts": 60,

   "max_position_embeddings": 32768,
   "max_window_layers": 21,
   "model_type": "qwen2_moe",
+  "moe_intermediate_size": 1376,
   "norm_topk_prob": false,
   "num_attention_heads": 16,
   "num_experts": 60,