Update app.py

app.py

@@ -2,11 +2,12 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("Zhengyi/LLaMA-Mesh")
-#client = InferenceClient("unsloth/Llama-3.2-1B-Instruct")
+
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("Zhengyi/LLaMA-Mesh")
+model = AutoModelForCausalLM.from_pretrained("Zhengyi/LLaMA-Mesh")
 
 
 def respond(