FloVolo
/

mistral-flo-finetune-2-T4

Text Generation

Generated from Trainer

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Voldimou commited on Feb 16

Commit

57849f1

•

1 Parent(s): 0c67153

Update handler.py

Files changed (1) hide show

handler.py +1 -1

handler.py CHANGED Viewed

@@ -28,7 +28,7 @@ class EndpointHandler:
         self.ft_model = PeftModel.from_pretrained(base_model, "FloVolo/mistral-flo-finetune-2-T4").to("cuda")
-    def __call__(self, data: Any):
         inputs = data.pop("inputs", data)
         model_input = self.eval_tokenizer(inputs, return_tensors="pt").to("cuda")

         self.ft_model = PeftModel.from_pretrained(base_model, "FloVolo/mistral-flo-finetune-2-T4").to("cuda")
+    def __call__(self, data):
         inputs = data.pop("inputs", data)
         model_input = self.eval_tokenizer(inputs, return_tensors="pt").to("cuda")