Update app.py

app.py

@@ -9,7 +9,7 @@ client = InferenceClient(api_key=api_key)
 def chat_with_model(prompt):
     response_text = ""
     for message in client.chat_completion(
-        model="google/gemma-2-2b-it",
+        model="dicta-il/dictalm-7b",
         messages=[{"role": "user", "content": prompt}],
         max_tokens=250,
         stream=True,
@@ -19,3 +19,6 @@ def chat_with_model(prompt):
 
 interface = gr.Interface(fn=chat_with_model, inputs="text", outputs="text", title="Chat with Hugging Face Model")
 interface.launch()
+
+
+#  model="google/gemma-2-2b-it" זה מודל שעבד