Update app.py

app.py

@@ -1,29 +1,15 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-# Use a pipeline as a high-level helper
-from transformers import pipeline
-
-messages = [
-    {"role": "user", "content": "Who are you?"},
-]
-pipe = pipeline("text-generation", model="arcee-ai/Arcee-Spark")
-pipe(messages)
-
-
-# Load model directly
 from transformers import AutoTokenizer, AutoModelForCausalLM
+from huggingface_hub import InferenceClient
 
+# Load tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained("arcee-ai/Arcee-Spark")
 model = AutoModelForCausalLM.from_pretrained("arcee-ai/Arcee-Spark")
 
-/*
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
+# Function to generate response
 def respond(
     message,
-    history: list[tuple[str, str]],
+    history,
     system_message,
     max_tokens,
     temperature,
@@ -39,39 +25,25 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    #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 = client.chat_completion(messages, max_tokens=max_tokens, temperature=temperature, top_p=top_p)
 
-        response += token
-        yield response
+    yield response  # Placeholder yield for response
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/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.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)",
-        ),
+# Define Gradio interface
+demo = gr.Interface(
+    fn=respond,
+    inputs=[
+        gr.Textbox(label="System message", default="You are a friendly Chatbot."),
+        gr.Slider(label="Max new tokens", minimum=1, maximum=2048, step=1, default=512),
+        gr.Slider(label="Temperature", minimum=0.1, maximum=4.0, step=0.1, default=0.7),
+        gr.Slider(label="Top-p (nucleus sampling)", minimum=0.1, maximum=1.0, step=0.05, default=0.95),
     ],
+    outputs=gr.Textbox(label="Response"),
+    title="Chatbot Demo",
 )
-*/
 
+# Launch Gradio interface
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()