Update app.py

app.py

@@ -18,9 +18,9 @@ quantization_config = BitsAndBytesConfig(
 )
 
 model = AutoModelForCausalLM.from_pretrained(
-    "meta-llama/Meta-Llama-3-8B-Instruct", quantization_config=quantization_config, token=token
+    "NousResearch/Hermes-2-Pro-Llama-3-8B", quantization_config=quantization_config, token=token
 )
-tok = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct", token=token)
+tok = AutoTokenizer.from_pretrained("NousResearch/Hermes-2-Pro-Llama-3-8B", token=token)
 terminators = [
     tok.eos_token_id,
     tok.convert_tokens_to_ids("<|eot_id|>")
@@ -105,6 +105,6 @@ demo = gr.ChatInterface(
     ],
     stop_btn="Stop Generation",
     title="Chat With LLMs",
-    description="Now Running [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) in 4bit"
+    description="Now Running [NousResearch/Hermes-2-Pro-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B) in 4bit"
 )
 demo.launch()