Update app.py

app.py

@@ -1,64 +1,87 @@
 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")
+# Define available models
+MODELS = {
+    "Zephyr 7B Beta": "HuggingFaceH4/zephyr-7b-beta",
+    "GPT-2": "gpt2",
+    "GPT-2 Medium": "gpt2-medium", 
+    "DistilGPT-2": "distilgpt2",
+    "German GPT-2": "german-nlp-group/german-gpt2",
+    "German Wechsel GPT-2": "benjamin/gpt2-wechsel-german",
+    "T5 Base": "t5-base",
+    "T5 Large": "t5-large"
+}
 
+def create_inference_client(model_name):
+    """Create an InferenceClient for the selected model."""
+    try:
+        return InferenceClient(model_name)
+    except Exception as e:
+        print(f"Error creating client for {model_name}: {e}")
+        return None
 
 def respond(
     message,
     history: list[tuple[str, str]],
     system_message,
+    model_name,
     max_tokens,
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
+    """Generate response using selected model."""
+    # Create client for selected model
+    client = create_inference_client(MODELS[model_name])
+    
+    if not client:
+        return "Error: Could not create model client."
 
+    # Prepare chat history
+    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})
 
-    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
-"""
-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)",
-        ),
-    ],
-)
+    # Generate response
+    try:
+        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 or ""
+            response += token
+            yield response
+    except Exception as e:
+        yield f"Error during generation: {e}"
 
+def create_chat_interface():
+    """Create Gradio ChatInterface with model selection."""
+    demo = gr.ChatInterface(
+        respond,
+        additional_inputs=[
+            gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+            gr.Dropdown(list(MODELS.keys()), value="Zephyr 7B Beta", label="Select Model"),
+            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)",
+            ),
+        ]
+    )
+    return demo
 
 if __name__ == "__main__":
-    demo.launch()
+    chat_interface = create_chat_interface()
+    chat_interface.launch(share=True)