Update app.py

app.py

@@ -6,7 +6,7 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from deepspeed.linear.config import QuantizationConfig
 
-Llamatokenizer = AutoTokenizer.from_pretrained(
+tokenizer = AutoTokenizer.from_pretrained(
     "Snowflake/snowflake-arctic-instruct",
     trust_remote_code=True
 )
@@ -24,7 +24,7 @@ model = AutoModelForCausalLM.from_pretrained(
 
 content = "5x + 35 = 7x - 60 + 10. Solve for x"
 messages = [{"role": "user", "content": content}]
-input_ids = Llamatokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to("cuda")
+input_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to("cuda")
 
 outputs = model.generate(input_ids=input_ids, max_new_tokens=256)
-print(Llamatokenizer.decode(outputs[0]))
+print(tokenizer.decode(outputs[0]))