Update app.py

app.py

@@ -1,13 +1,12 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-# Inference
-#model_text = "microsoft/Phi-4-mini-instruct"
-model_text = "microsoft/Phi-3.5-mini-instruct"
-
 client = InferenceClient()
 
-def fn_text(
+# Phi 3
+model_phi_3 = "microsoft/Phi-3.5-mini-instruct"
+
+def fn_phi_3(
     prompt,
     history,
     system_prompt,
@@ -16,17 +15,67 @@ def fn_text(
     top_p,
 ):
 
+    # With System Prompt
     messages = [{"role": "system", "content": system_prompt}]
     history.append(messages[0])
+    messages.append({"role": "user", "content": prompt})
+    history.append(messages[1])
+
+    # Without System Prompt
+    #messages = [{"role": "user", "content": prompt}]
+    #history.append(messages[0])
+
+    stream = client.chat.completions.create(
+        model = model_phi_3,
+        messages = history,
+        max_tokens = max_tokens,
+        temperature = temperature,
+        top_p = top_p,
+        stream = True,
+    )
+
+    chunks = []
+    for chunk in stream:
+        chunks.append(chunk.choices[0].delta.content or "")
+        yield "".join(chunks)
 
+app_phi_3 = gr.ChatInterface(
+    fn = fn_phi_3,
+    type = "messages",
+    additional_inputs = [
+        gr.Textbox(value="You are a helpful assistant.", label="System Prompt"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max 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"),
+    ],
+    title = "Microsoft Phi 3",
+    description = model_phi_3,
+)
+
+# Phi 4
+model_phi_4 = "microsoft/phi-4"
+
+def fn_phi_4(
+    prompt,
+    history,
+    system_prompt,
+    max_tokens,
+    temperature,
+    top_p,
+):
+
+    # With System Prompt
+    messages = [{"role": "system", "content": system_prompt}]
+    history.append(messages[0])
     messages.append({"role": "user", "content": prompt})
     history.append(messages[1])
 
+    # Without System Prompt
     #messages = [{"role": "user", "content": prompt}]
     #history.append(messages[0])
 
     stream = client.chat.completions.create(
-        model = model_text,
+        model = model_phi_4,
         messages = history,
         max_tokens = max_tokens,
         temperature = temperature,
@@ -39,8 +88,8 @@ def fn_text(
         chunks.append(chunk.choices[0].delta.content or "")
         yield "".join(chunks)
 
-app_text = gr.ChatInterface(
-    fn = fn_text,
+app_phi_4 = gr.ChatInterface(
+    fn = fn_phi_4,
     type = "messages",
     additional_inputs = [
         gr.Textbox(value="You are a helpful assistant.", label="System Prompt"),
@@ -48,11 +97,11 @@ app_text = gr.ChatInterface(
         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"),
     ],
-    title = "Microsoft Phi",
-    description = model_text,
+    title = "Microsoft Phi 4",
+    description = model_phi_4,
 )
 
 app = gr.TabbedInterface(
-    [app_text],
-    ["Text"]
+    [app_phi_3, app_phi_4],
+    ["Phi 3", "Phi 4"]
 ).launch()