Update app.py

app.py

@@ -1,63 +1,34 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import pipeline
 
-"""
-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("JamesBentley/Llama-2-7b-chat-hf-fine-tuned")
+# Initialize the pipeline with the specific model
+pipe = pipeline("text-generation", model="JamesBentley/Llama-2-7b-chat-hf-fine-tuned")
 
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    # Build the conversation history for the model
     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.extend([{"role": "user" if role == 'user' else "assistant", "content": content} for role, content in history])
     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 += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+    
+    # Generate the response using the model
+    response = pipe(messages, max_length=max_tokens, temperature=temperature, top_p=top_p, num_return_sequences=1)
+    
+    # Extract text from response (assumes single response generation)
+    return response[0]['generated_text']
+
+# Setup Gradio 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)",
-        ),
+    fn=respond,
+    inputs=[
+        gr.Textbox(label="Your message"),
+        gr.Dataframe(headers=["Role", "Content"], label="Conversation History"),
+        gr.Textbox(default="You are a friendly Chatbot.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, default=512, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=1.0, default=0.7, label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=1.0, default=0.95, label="Top-p (nucleus sampling)")
     ],
+    outputs=[gr.Textbox(label="Response")]
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()