Update app.py

app.py

@@ -1,70 +1,104 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(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,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = 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
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    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)",
-        ),
-    ],
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+import torch
+
+# --- Load tokenizer and model for CPU ---
+tokenizer = AutoTokenizer.from_pretrained("unsloth/Qwen3-1.7B")
+
+base_model = AutoModelForCausalLM.from_pretrained(
+    "unsloth/Qwen3-1.7B",
+    torch_dtype=torch.float32,
+    device_map={"": "cpu"},
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+model = PeftModel.from_pretrained(base_model, "khazarai/Nizami-1.7B").to("cpu")
+
+
+# --- Chatbot logic ---
+def generate_response(user_input, chat_history):
+    if not user_input.strip():
+        return chat_history, chat_history
+
+    chat_history.append({"role": "user", "content": user_input})
+
+    text = tokenizer.apply_chat_template(
+        chat_history,
+        tokenize=False,
+        add_generation_prompt=True,
+        enable_thinking=False,
+    )
+
+    inputs = tokenizer(text, return_tensors="pt").to("cpu")
+
+    output_tokens = model.generate(
+        **inputs,
+        max_new_tokens=1024,
+        temperature=0.7,
+        top_p=0.8,
+        top_k=20,
+        do_sample=True 
+    )
+
+    response = tokenizer.decode(output_tokens[0], skip_special_tokens=True)
+    response = response.split(user_input)[-1].strip()
+
+    chat_history.append({"role": "assistant", "content": response})
+
+    gr_chat_history = [
+        (m["content"], chat_history[i + 1]["content"])
+        for i, m in enumerate(chat_history[:-1])
+        if m["role"] == "user"
+    ]
+
+    return gr_chat_history, chat_history
+
+
+# --- UI Design ---
+with gr.Blocks(theme=gr.themes.Soft(primary_hue="yellow", secondary_hue="slate")) as demo:
+    gr.HTML("""
+    <div style="text-align: center; margin-bottom: 20px;">
+        <h1 style="font-family: 'Inter', sans-serif; font-weight: 800; color: #FACC15; font-size: 2.2em;">
+            📚 Nizami-1.7B
+        </h1>
+        <p style="color: #FDE047; font-size: 1.05em; margin-top: -10px;">
+            Academic style comprehension and reasoning in Azerbaijani.
+        </p>
+    </div>
+    """)
+
+    with gr.Row():
+        with gr.Column(scale=6):
+            chatbot = gr.Chatbot(
+                label="Academic-style Chat",
+                height=600,
+                bubble_full_width=True,
+                show_copy_button=True,
+                avatar_images=(
+                    "https://cdn-icons-png.flaticon.com/512/1077/1077012.png",  # user icon
+                    "https://cdn-icons-png.flaticon.com/512/4140/4140048.png",  # bot icon
+                ),
+            )
+            user_input = gr.Textbox(
+                placeholder="Ask me...",
+                label="💬 Your question",
+                lines=3,
+                autofocus=True,
+            )
+            with gr.Row():
+                send_btn = gr.Button("🚀 Send", variant="primary")
+                clear_btn = gr.Button("🧹 Clear Chat")
+
+    state = gr.State([])
+
+    send_btn.click(generate_response, [user_input, state], [chatbot, state])
+    user_input.submit(generate_response, [user_input, state], [chatbot, state])
+    clear_btn.click(lambda: ([], []), None, [chatbot, state])
 
+    gr.HTML("""
+    <div style="text-align: center; margin-top: 25px; color: #6B7280; font-size: 0.9em;">
+        Powered by <b>Qwen3-1.7B + Nizami-1.7B</b> | Built with ❤️ using Gradio
+    </div>
+    """)
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch(share=True)