Update app.py

app.py

@@ -1,12 +1,10 @@
 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")
-
+# Connect to your model on Hugging Face Hub
+client = InferenceClient("JK-TK/bible2")
 
+# Define the response function
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -15,50 +13,35 @@ def respond(
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
+    # Construct a flat prompt: system + history + current message
+    prompt = system_message.strip() + "\n\n"
+    for user, assistant in history:
+        prompt += f"User: {user}\nAssistant: {assistant}\n"
+    prompt += f"User: {message}\nAssistant:"
 
+    # Generate response from model using text-generation
     response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    for token in client.text_generation(
+        prompt,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
+        stream=True,
     ):
-        token = message.choices[0].delta.content
-
         response += token
         yield response
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Create the chat interface
 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.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+        gr.Textbox(value="You are a biblical AI assistant.", label="System message"),
+        gr.Slider(minimum=1, maximum=1024, value=300, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=2.0, value=0.8, step=0.1, label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p"),
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()