Update app.py

app.py

@@ -10,7 +10,10 @@ models=[
     "facebook/MobileLLM-1B",
 ]
 client_z=[]
+# Use a pipeline as a high-level helper
+from transformers import pipeline
 
+#pipe = pipeline("text-generation", model="facebook/MobileLLM-125M", trust_remote_code=True)
 
 def load_models(inp,new_models):
     if not new_models:
@@ -21,7 +24,8 @@ def load_models(inp,new_models):
     #print(new_models[inp[0]])
     client_z.clear()
     for z,ea in enumerate(inp):
-        client_z.append(InferenceClient(new_models[inp[z]]))
+        #client_z.append(InferenceClient(new_models[inp[z]]))
+        client_z.append(pipeline("text-generation", model=new_models[inp[z]], trust_remote_code=True))
         out_box[z]=(gr.update(label=new_models[inp[z]]))
     return out_box[0],out_box[1],out_box[2],out_box[3]
 def format_prompt_default(message, history):