Update services/strategy.py

services/strategy.py

@@ -68,7 +68,7 @@ class BestOfN(GenerationStrategy):
 
 
             # Simple inference example
-            prm_output = llm(
+            prm_output = generator.prm_model(
               "<|system|>\n{system_message}</s>\n<|user|>\n{response}</s>\n<|assistant|>", # Prompt
               max_tokens=512,  # Generate up to 512 tokens
               stop=["</s>"],   # Example stop token - not necessarily correct for this specific model! Please check before using.