Update app.py

app.py

@@ -1,13 +1,19 @@
 import gradio as gr
 import os
 from huggingface_hub import InferenceClient
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
 """
 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
 """
 
 access_token = os.getenv('HF_TOKEN')
-client = InferenceClient("Mikhil-jivus/Llama-32-3B-FineTuned",token = access_token)
+# Load the tokenizer and model from the Hugging Face repository
+tokenizer = AutoTokenizer.from_pretrained(repo_id, token=access_token)
+
+
+client = InferenceClient("text-generation",model="Mikhil-jivus/Llama-32-3B-FineTuned",tokenizer=tokenizer,token = access_token)
 
 
 def respond(