Qwen
/

Qwen2-57B-A14B-Instruct-GPTQ-Int4

Text Generation

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

hzhwcmhf commited on Jun 6, 2024

Commit

4c75676

·

verified ·

1 Parent(s): fc1bf15

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -238,7 +238,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 18944,
   "max_position_embeddings": 32768,
-  "max_window_layers": 21,
   "mlp_only_layers": [],
   "model_type": "qwen2_moe",
   "moe_intermediate_size": 2560,

   "initializer_range": 0.02,
   "intermediate_size": 18944,
   "max_position_embeddings": 32768,
+  "max_window_layers": 28,
   "mlp_only_layers": [],
   "model_type": "qwen2_moe",
   "moe_intermediate_size": 2560,