Update app.py

app.py

@@ -14,10 +14,6 @@ print(zero.device) # <-- 'cpu' 🤔
 
 @spaces.GPU
 def greet(prompts, separator):
-    print('prompts:')
-    print(prompts)
-    print('separator')
-    print(separator)
     # print(zero.device) # <-- 'cuda:0' 🤗
     from vllm import SamplingParams, LLM
     from transformers.utils import move_cache
@@ -42,6 +38,11 @@ def greet(prompts, separator):
         prompts = prompts.split('separator')
     else:
         prompts = [prompts]
+    for idx, pt in enumerate(prompts):
+        print()
+        print(f'[{idx}]:')
+        print(pt)
+        
     model_outputs = model.generate(prompts, sampling_params)
     generations = []
     for output in model_outputs: