Update app.py

app.py

@@ -72,7 +72,7 @@ def generate(title, abstract):
         f"### Human: {prompt + doc} \n"
         f"### Assistant:"
     )
-    inputs = tok(formatted_prompt, return_tensors="pt").to("cuda:1")
+    inputs = tok(formatted_prompt, return_tensors="pt")#.to("cuda:1")
     outputs = m.generate(inputs=inputs.input_ids, max_new_tokens=300)
     output = tok.decode(outputs[0], skip_special_tokens=True)
     index_response = output.find("### Assistant: ") + 15
@@ -122,7 +122,7 @@ def generate(title, abstract):
             f"### Human: {prompt} \n"
             f"### Assistant:"
         )
-        inputs = tok(formatted_prompt, return_tensors="pt").to("cuda:2")
+        inputs = tok(formatted_prompt, return_tensors="pt")#.to("cuda:2")
         outputs = m.generate(inputs=inputs.input_ids, max_new_tokens=300)
         output = tok.decode(outputs[0], skip_special_tokens=True)
         index_response = output.find("### Assistant: ") + 15