Qwen
/

Qwen2-1.5B-Instruct-GPTQ-Int8

Text Generation

text-generation-inference

Inference Endpoints

8-bit precision

Model card Files Files and versions Community

feihu.hf commited on Jun 6

Commit

4d9607d

•

1 Parent(s): 3f0a3dc

update generation_config.json

Files changed (1) hide show

generation_config.json +2 -2

generation_config.json CHANGED Viewed

@@ -6,9 +6,9 @@
     151645,
     151643
   ],
-  "repetition_penalty": 1.05,
   "temperature": 0.7,
   "top_p": 0.8,
   "top_k": 20,
   "transformers_version": "4.37.0"
-}

     151645,
     151643
   ],
+  "repetition_penalty": 1.1,
   "temperature": 0.7,
   "top_p": 0.8,
   "top_k": 20,
   "transformers_version": "4.37.0"
+}