Update app.py

app.py

@@ -47,10 +47,20 @@ def givetext(input_text,lmodel,ltokenizer):
         eval_prompt_pt2="\n\n\n### Response:\n"
         eval_prompt=eval_prompt_pt1+input_text+eval_prompt_pt2
         print(eval_prompt,"\n\n")
+
+        print("BEFORE PROCESSING MODEL INPUT")
+        
         model_input = ltokenizer(eval_prompt, return_tensors="pt").to("cpu")
+
+        PRINT(" BEFORE EVAL LMODEL")
         
         lmodel.eval()
+
+        PRINT("BEFORE DOING TORCH.NO_GRAD()")
+        
         with torch.no_grad():
+            PRINT("BEFORE RETURNING")
+            
             return (ltokenizer.decode(lmodel.generate(**model_input, max_new_tokens=1000)[0], skip_special_tokens=True))
             #return (ltokenizer.decode(lmodel.generate(**model_input, max_new_tokens=100)[0], skip_special_tokens=True))
     except Exception as error:
@@ -58,6 +68,7 @@ def givetext(input_text,lmodel,ltokenizer):
         #txt1 = "My name is {fname}, I'm {age}".format(fname = "John", age = 36)
 
 def mental_chat(message, history):
+    PRINT("BEFORE CALLING GIVETEXT")
     return givetext(message,newmodel,newtokenizer)
 
 demo = gr.ChatInterface(mental_chat)