Update app.py

app.py

@@ -5,15 +5,13 @@ print("Token loaded")
 import transformers
 import torch
 
-#Loading llama3 model
-model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
-
-pipeline = transformers.pipeline(
-"text-generation",
-model=model_id,
-model_kwargs={"torch_dtype": torch.bfloat16},
-device="cuda",
-)
+# Load the tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct", device_map="auto")  # to("cuda:0") 
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
 
 print("llama download successfully")