Update handler.py

handler.py

@@ -8,10 +8,7 @@ from transformers import pipeline
 # Load model directly
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("rwitz/go-bruins-v2")
-model = AutoModelForCausalLM.from_pretrained("rwitz/go-bruins-v2")
-
-pipe = pipeline("text-generation", model=model,tokenizer=tokenizer,device=0,torch_dtype=torch.bfloat16)
+pipe = pipeline("text-generation", model="rwitz/go-bruins-v2",device=0,torch_dtype=torch.bfloat16)
 ## load your model(s) into vram here
 
 def handler(event):