Update app.py

app.py

@@ -8,8 +8,9 @@ from transformers import pipeline
 #pipe = pipeline("text-generation", model="microsoft/Phi-3-mini-128k-instruct", trust_remote_code=True)
 
 #client = InferenceClient("microsoft/Phi-3-mini-128k-instruct")
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+#client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 #client = InferenceClient("google/gemma-1.1-7b-it")
+pipe = pipeline("text-generation", model="segolilylabs/Lily-Cybersecurity-7B-v0.2")
 
 
 @spaces.GPU
@@ -33,7 +34,7 @@ def respond(
 
     response = ""
 
-    for message in client.chat_completion(
+    for message in pipe.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,