fearf

app.py

@@ -28,7 +28,7 @@ subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENT
 
 @spaces.GPU
 def model_inference(
-    images, text, assistant_prefix= None, decoding_strategy = "Greedy", temperature= 0.4, max_new_tokens=512,
+    images, text, assistant_prefix= "Répond en faisant de belles phrases", decoding_strategy = "Greedy", temperature= 0.4, max_new_tokens=512,
     repetition_penalty=1.2, top_p=0.8
 ):
     ## Load idefics