Update app.py

app.py

@@ -14,7 +14,7 @@ from datetime import datetime
 from huggingface_hub import HfApi, hf_hub_download
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 model_name = "Woziii/llama-3-8b-chat-me"
-model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16, load_in_8bit=True)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 MAX_MAX_NEW_TOKENS = 250