Update app.py

app.py

@@ -3,7 +3,9 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 import gradio as gr
 
 model_id = "meta-llama/Llama-3.1-8B-Instruct"
-token = os.getenv("kumar")
+
+# Load the token from Hugging Face secrets (you must have set it in the "Secrets" tab as `HF_TOKEN`)
+token = os.getenv("kumar")  # ✅ Change 'kumar' to 'HF_TOKEN'
 
 tokenizer = AutoTokenizer.from_pretrained(model_id, token=token)
 model = AutoModelForCausalLM.from_pretrained(model_id, token=token, device_map="auto")
@@ -14,4 +16,5 @@ def chat_with_llama(prompt):
     result = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7)
     return result[0]["generated_text"]
 
-gr.Interface(fn=chat_with_llama, inputs="text", outputs="text", title="Venkat's Chatbot").launch()
+# ✅ Enable public sharing by setting `share=True`
+gr.Interface(fn=chat_with_llama, inputs="text", outputs="text", title="Venkat's Chatbot").launch(share=True)