Update app.py

app.py

@@ -3,7 +3,7 @@ import os
 os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
 
 import torch
-from transformers import AutoModel, AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer
 from deepspeed.linear.config import QuantizationConfig
 
 Llamatokenizertokenizer = AutoTokenizer.from_pretrained(
@@ -12,7 +12,7 @@ Llamatokenizertokenizer = AutoTokenizer.from_pretrained(
 )
 quant_config = QuantizationConfig(q_bits=8)
 
-model = AutoModel.from_pretrained(
+model = AutoModelForCausalLM.from_pretrained(
     "Snowflake/snowflake-arctic-instruct",
     trust_remote_code=True,
     low_cpu_mem_usage=True,