Update handler.py

handler.py

@@ -6,7 +6,7 @@ sleep_time = int(os.environ.get('SLEEP_TIME', 3))
 # Use a pipeline as a high-level helper
 from transformers import pipeline
 
-pipe = pipeline("text-generation", model="rwitz/go-bruins-v2",device=0,torch_dtype=torch.bfloat16)
+pipe = pipeline("text-generation", model="rwitz/go-bruins-v2",device=0,torch_dtype=torch.bfloat16,cache_dir="/workspace")
 ## load your model(s) into vram here
 
 def handler(event):