Update app.py

app.py

@@ -1,11 +1,14 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
 """
 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("HuggingFaceH4/zephyr-7b-beta")
+# Load model directly
 
+tokenizer = AutoTokenizer.from_pretrained("Navid-AI/Mulhem-1-Mini")
+model = AutoModelForCausalLM.from_pretrained("Navid-AI/Mulhem-1-Mini", torch_dtype=torch.bfloat16, device_map="auto", attn_implementation="flash_attention_2", token=os.getenv("HF_TOKEN"))
 
 def respond(
     message,