Qwen
/

Qwen1.5-MoE-A2.7B-Chat-GPTQ-Int4

Text Generation

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

bzheng commited on Mar 28

Commit

825f562

•

1 Parent(s): 5132be9

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -249,7 +249,7 @@
   "rope_theta": 1000000.0,
   "router_aux_loss_coef": 0.001,
   "shared_expert_intermediate_size": 5632,
-  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.39.0.dev0",

   "rope_theta": 1000000.0,
   "router_aux_loss_coef": 0.001,
   "shared_expert_intermediate_size": 5632,
+  "sliding_window": 32768,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.39.0.dev0",