LanguageMachines
/

blip2-flan-t5-xxl

visual-question-answering

image-captioning

Inference Endpoints

Model card Files Files and versions Community

sarang-shrivastava commited on Jun 28, 2023

Commit

cd7fc31

•

1 Parent(s): 9a14462

Update handler

Files changed (1) hide show

handler.py +1 -1

handler.py CHANGED Viewed

@@ -83,7 +83,7 @@ class EndpointHandler():
         # question = "how many dogs are in the picture?"
         # inputs = self.processor(raw_image, question, return_tensors="pt").to("cuda")
-        inputs = self.processor([raw_image]*batch_size, return_tensors="pt").to("cuda")
         out = self.model.generate(**inputs)

         # question = "how many dogs are in the picture?"
         # inputs = self.processor(raw_image, question, return_tensors="pt").to("cuda")
+        inputs = self.processor([raw_image]*batch_size, return_tensors="pt").to("cuda", torch.float16)
         out = self.model.generate(**inputs)