Update handler.py

increasing token limit

handler.py

@@ -10,7 +10,8 @@ dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] == 8 else torch.
 class EndpointHandler:
     def __init__(self, path=""):
         # load the model
-        tokenizer = AutoTokenizer.from_pretrained(path)        
+        tokenizer = AutoTokenizer.from_pretrained(path) 
+        tokenizer..max_seq_len = 8192
         model = AutoModelForCausalLM.from_pretrained(path, device_map="auto", torch_dtype=dtype, trust_remote_code=True)
         model.to('cuda:0')