change model

app.py

@@ -3,7 +3,7 @@ from huggingface_hub import InferenceClient
 import spaces
 from transformers import pipeline
 
-pipe = pipeline("text-generation", model="HuggingFaceH4/zephyr-7b-beta")
+pipe = pipeline("image-text-to-text", model="HuggingFaceTB/SmolVLM2-2.2B-Instruct")
 
 @spaces.GPU
 def respond(
@@ -22,7 +22,7 @@ def respond(
 
     response = ""
 
-    for message in pipe.chat_completion(
+    for message in pipe(
         messages,
         max_tokens=max_tokens,
         stream=True,