Update app.py

app.py

@@ -18,9 +18,9 @@ quantization_config = BitsAndBytesConfig(
 )
 
 model = AutoModelForCausalLM.from_pretrained(
-    "meta-llama/Meta-Llama-3-70B-Instruct", quantization_config=quantization_config, token=token
+    "meta-llama/Meta-Llama-3-8B-Instruct", quantization_config=quantization_config, token=token
 )
-tok = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-70B-Instruct", token=token)
+tok = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct", token=token)
 
 if torch.cuda.is_available():
     device = torch.device("cuda")
@@ -104,6 +104,6 @@ demo = gr.ChatInterface(
     ],
     stop_btn="Stop Generation",
     title="Chat With LLMs",
-    description="Now Running ![meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) in 4bit"
+    description="Now Running ![meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) in 4bit"
 )
 demo.launch()