Update app.py

app.py

@@ -3,16 +3,23 @@ import os
 os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
 
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import LlamaForCausalLM, LlamaTokenizer
+#from transformers import AutoModelForCausalLM, AutoTokenizer
 from deepspeed.linear.config import QuantizationConfig
 
-tokenizer = AutoTokenizer.from_pretrained(
+
+from transformers import LlamaForCausalLM, LlamaTokenizer
+
+
+#tokenizer = AutoTokenizer.from_pretrained(
+tokenizer = LlamaTokenizer.from_pretrained(
     "Snowflake/snowflake-arctic-instruct",
     trust_remote_code=True
 )
 quant_config = QuantizationConfig(q_bits=8)
+#model = AutoModelForCausalLM.from_pretrained(
 
-model = AutoModelForCausalLM.from_pretrained(
+model = LlamaForCausalLM.from_pretrained(
     "Snowflake/snowflake-arctic-instruct",
     trust_remote_code=True,
     low_cpu_mem_usage=True,