try with gemma3 27b it

app.py

@@ -0,0 +1,55 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+
+
+client = InferenceClient("google/gemma-3-27b-it")
+
+
+def answer(
+    message,
+    historical_information: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
+    for comp in historical_information:
+        if comp[0]:
+            messages.append({"role": "user", "content": comp[0]})
+        if comp[1]:
+            messages.append({"role": "assistant", "content": comp[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
+
+
+demo = gr.ChatInterface(
+    answer,
+    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)",
+        ),
+    ],
+)
+
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1 @@
+huggingface_hub