Update app.py

app.py

@@ -46,4 +46,16 @@ def generate_chat_completion(messages, max_tokens=560, temperature=0.7):
             "completion_tokens": len(response.split()),
             "total_tokens": len(prompt.split()) + len(response.split())
         }
-    }
+    }
+
+    from transformers import AutoTokenizer
+
+# Add after model loading
+tokenizer = AutoTokenizer.from_pretrained(
+    "mradermacher/Ninja-v1-NSFW-RP-GGUF", 
+    use_fast=False
+)
+
+# In generate_chat_completion():
+prompt_tokens = len(tokenizer.encode(prompt))
+completion_tokens = len(tokenizer.encode(response))