Update app.py

app.py

@@ -3,15 +3,14 @@ import pprint
 import subprocess
 from threading import Thread
 from transformers import AutoTokenizer, TextIteratorStreamer
-
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
 result = subprocess.run(["lscpu"], text=True, capture_output=True)
 pprint.pprint(result.stdout)
 
 
-checkpoint = "suriya7/Gemma-2b-SFT"
-tokenizer = AutoTokenizer.from_pretrained(checkpoint)
-model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)
+tokenizer = AutoTokenizer.from_pretrained("suriya7/Gemma-2b-SFT")
+model = AutoModelForCausalLM.from_pretrained("suriya7/Gemma-2b-SFT")
 
 
 def run_generation(user_text, top_p, temperature, top_k, max_new_tokens):