ydshieh
/

vit-gpt2-coco-en

vision-encoder-decoder

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

ydshieh HF staff commited on Oct 25, 2021

Commit

117d46a

•

1 Parent(s): 25a7779

Update pipeline.py

Files changed (1) hide show

pipeline.py +1 -1

pipeline.py CHANGED Viewed

@@ -20,7 +20,7 @@ class PreTrainedPipeline():
         max_length = 16
         num_beams = 4
         # self.gen_kwargs = {"max_length": max_length, "num_beams": num_beams}
-        self.gen_kwargs = {"max_length": max_length, "num_beams": num_beams, return_dict_in_generate=True}
         self.model.to("cpu")
         self.model.eval()

         max_length = 16
         num_beams = 4
         # self.gen_kwargs = {"max_length": max_length, "num_beams": num_beams}
+        self.gen_kwargs = {"max_length": max_length, "num_beams": num_beams, "return_dict_in_generate": True}
         self.model.to("cpu")
         self.model.eval()