YingxuHe
/

chatglm3-6b-chitchat

Inference Endpoints

Model card Files Files and versions Community

Yingxu He commited on Oct 29

Commit

adc32dd

•

1 Parent(s): 2b89104

Update handler.py

Files changed (1) hide show

handler.py +1 -1

handler.py CHANGED Viewed

@@ -14,7 +14,7 @@ ASSISTANT_SYMBOL = "<||assistant_symbol||>"
 class EndpointHandler:
     def __init__(self, path=""):
         # load the model
-        self.pipeline = chatglm_cpp.Pipeline(f"{path}/q5_1.bin")
     def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
         inputs = data.pop("inputs", data)

 class EndpointHandler:
     def __init__(self, path=""):
         # load the model
+        self.pipeline = chatglm_cpp.Pipeline(f"{path}/q8_0_v2.bin")
     def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
         inputs = data.pop("inputs", data)