Update app.py

app.py

@@ -8,7 +8,7 @@ import bitsandbytes, flash_attn
 
 tokenizer = LlamaTokenizer.from_pretrained('NousResearch/Nous-Hermes-2-Mistral-7B-DPO', trust_remote_code=True)
 model = MixtralForCausalLM.from_pretrained(
-    "NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
+    "NousResearch/Nous-Hermes-2-Mistral-7B-DPO-GGUF",
     torch_dtype=torch.float16,
     device_map="auto",
     load_in_8bit=False,