Update app.py

app.py

@@ -1,11 +1,9 @@
 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("HuggingFaceH4/zephyr-7b-beta")
+from transformers import pipeline
 
+# Load your model
+model_name = "Atulit23/meta-llama-indian-constitution"
+pipe = pipeline("text-generation", model=model_name)
 
 def respond(
     message,
@@ -25,28 +23,15 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    response = pipe(messages[-1]["content"], max_length=max_tokens, temperature=temperature, top_p=top_p)
+    return response[0]['generated_text']
 
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Create a Gradio ChatInterface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Textbox(value="You are a friendly Chatbot focused on the Indian Constitution.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=50, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
             minimum=0.1,
@@ -56,8 +41,9 @@ demo = gr.ChatInterface(
             label="Top-p (nucleus sampling)",
         ),
     ],
+    title="Constitutional Chatbot",
+    description="Ask questions related to the Indian Constitution."
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()