Updated Gemma chatbot

Tabs/Gemma_Chatbot.py

@@ -0,0 +1,82 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+HF_TOKEN = os.getenv("HF_TOKEN")
+
+model_list = ["google/gemma-2-2b-it", "google/gemma-2-9b-it", "google/gemma-2-27b-it"]
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    model_id,
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    client = InferenceClient(
+        model_id,
+        token=HF_TOKEN,
+    )
+    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
+
+gemma_chatbot = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Dropdown(
+            choices=model_list,
+            label="Model",
+            value="google/gemma-2-27b-it",
+        ),
+        gr.Textbox(
+            value="You are a friendly Chatbot.",
+            label="System message"
+        ),
+        gr.Slider(
+            minimum=1,
+            maximum=4096,
+            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)",
+        ),
+    ],
+)

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 from Tabs.Gemini_Chabot_Stable import gemini_chatbot, clear_chat_button, undo_chat_button, clear_chat_history, undo_chat, TITLE, NOTICE, ERRORS, FUTURE_IMPLEMENTATIONS, ABOUT
 from Tabs.Gemini_Chatbot_Preview import gemini_chatbot_preview, clear_chat_button_preview, undo_chat_button_preview, clear_chat_history_preview, undo_chat_preview
+from Tabs.Gemma_Chatbot import gemma_chatbot
 
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
     gr.HTML("""<h3 align="center">I strongly recommond duplicating this space for intensive uses!!!</h3>""")
@@ -20,10 +21,6 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
             fn=undo_chat
         )
     # ============================== Stable - END ==============================
-
-    with gr.Tab("Chat with Gemma 2"):
-        gr.HTML("""<h1 align="center">Still in development</h1>""")
-
     # ============================== Nightly - START ==============================
     with gr.Tab("Chat with Gemini 1.5 - Preview"):
         gemini_chatbot_preview.render()
@@ -34,5 +31,7 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
             fn=undo_chat_preview
         )
     # ============================== Nightly - END ==============================
+    with gr.Tab("Chat with Gemma 2"):
+        gemma_chatbot.render()
 
 demo.queue().launch(debug=True, show_error=True)