Update app.py

app.py

@@ -22,6 +22,10 @@ def inference(raw_image, question, decoding_strategy):
         inputs["do_sample"] = True
         inputs["top_k"] = 50
         inputs["top_p"] = 0.95
+    elif decoding_strategy == "Contrastive search":
+        inputs["penalty_alpha"] = 0.6
+        inputs["top_k"] = 4
+        inputs["max_length"] = 512
 
     out = model_image_captioning.generate(**inputs)
     return processor.batch_decode(out, skip_special_tokens=True)[0]
@@ -29,7 +33,7 @@ def inference(raw_image, question, decoding_strategy):
 inputs = [
         gr.inputs.Image(type='pil'),
         gr.inputs.Textbox(lines=2, label="Context (optional)"),
-        gr.inputs.Radio(choices=['Beam search','Nucleus sampling'], type="value", default="Nucleus sampling", label="Caption Decoding Strategy")
+        gr.inputs.Radio(choices=["Beam search","Nucleus sampling", "Contrastive search"], type="value", default="Nucleus sampling", label="Caption Decoding Strategy")
     ]
 outputs = gr.outputs.Textbox(label="Output")