modified: app.py

app.py

@@ -8,7 +8,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 checkpoint = "Pipatpong/vcm_santa"
 device = "cuda" if torch.cuda.is_available() else "cpu"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint, trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained(checkpoint, trust_remote_code=True, device_map="auto", load_in_8bit=True)
+model = AutoModelForCausalLM.from_pretrained(checkpoint, trust_remote_code=True, device_map="auto")
 
 def generate(text, max_length, num_return_sequences=1):
     inputs = tokenizer.encode(text, padding=False, add_special_tokens=False, return_tensors="pt")