Qwen
/

Qwen1.5-14B-Chat-GPTQ-Int8

Text Generation

text-generation-inference

Inference Endpoints

8-bit precision

Model card Files Files and versions Community

clonefy commited on Feb 5

Commit

e8033fa

•

1 Parent(s): 4fbf925

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -41,7 +41,7 @@
   },
   "rms_norm_eps": 1e-06,
   "rope_theta": 1000000.0,
-  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.37.0",

   },
   "rms_norm_eps": 1e-06,
   "rope_theta": 1000000.0,
+  "sliding_window": 32768,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.37.0",