Update app.py

app.py

@@ -3,20 +3,22 @@ import os
 os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
 
 import torch
-#from transformers import LlamaForCausalLM, LlamaTokenizer
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoModelForCausalLM
+from transformers import pipeline
+#from transformers import AutoModelForCausalLM, AutoTokenizer
 from deepspeed.linear.config import QuantizationConfig
 
+# Load model directly
+#model = AutoModelForCausalLM.from_pretrained("Snowflake/snowflake-arctic-instruct", trust_remote_code=True)
+
+
+pipe = pipeline("text-generation", model="Snowflake/snowflake-arctic-instruct", trust_remote_code=True)
+
+#tokenizer = AutoTokenizer.from_pretrained("Snowflake/snowflake-arctic-instruct",trust_remote_code=True)
 
 
-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 = LlamaForCausalLM.from_pretrained(
     "Snowflake/snowflake-arctic-instruct",
     trust_remote_code=True,
     low_cpu_mem_usage=True,