Update app.py

app.py

@@ -3,10 +3,23 @@
 #importing the required libraries including transformers
 import gradio as gr
 from huggingface_hub import InferenceClient
-from transformers import pipeline
+from transformers import pipeline,AutoModelForCausalLM, AutoTokenizer
+import torch
+
+
+# Load model and tokenizer
+model_name = "meta-llama/Llama-2-7b-chat-hf"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
+
+def chat(input_text, history=[]):
+    history.append(input_text)
+    prompt = "\n".join(history) + "\nAI:"  # Simple conversational format
+    inputs = tokenizer(prompt, retur
+
+
+
 
-from huggingface_hub import login
-login()
 
 """
 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