Update app.py

app.py

@@ -1,70 +1,69 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
+from peft import PeftModel
+import torch
 
+# --- Load tokenizer and model ---
+tokenizer = AutoTokenizer.from_pretrained("unsloth/Qwen3-1.7B")
+base_model = AutoModelForCausalLM.from_pretrained(
+    "unsloth/Qwen3-1.7B",
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+model = PeftModel.from_pretrained(base_model, "khazarai/BioGenesis-ToT")
 
-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")
+# --- Define chatbot logic ---
+def generate_response(user_input, chat_history):
+    # Append user message to history
+    chat_history.append({"role": "user", "content": user_input})
 
-    messages = [{"role": "system", "content": system_message}]
+    # Convert history to prompt
+    text = tokenizer.apply_chat_template(
+        chat_history,
+        tokenize=False,
+        add_generation_prompt=True,
+        enable_thinking=True,
+    )
 
-    messages.extend(history)
+    # Tokenize and send to GPU
+    inputs = tokenizer(text, return_tensors="pt").to("cuda")
 
-    messages.append({"role": "user", "content": message})
+    # Generate
+    output_tokens = model.generate(
+        **inputs,
+        max_new_tokens=1200,
+        temperature=0.6,
+        top_p=0.95,
+        top_k=20,
+    )
 
-    response = ""
+    # Decode output
+    response = tokenizer.decode(output_tokens[0], skip_special_tokens=True)
 
-    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
+    # Extract only model's reply (avoid repeating prompt)
+    response = response.split(user_input)[-1].strip()
 
-        response += token
-        yield response
+    # Add model reply to chat history
+    chat_history.append({"role": "assistant", "content": response})
+    
+    # Prepare Gradio display format
+    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
 
+# --- Launch Gradio interface ---
+with gr.Blocks() as demo:
+    gr.Markdown("## 🧬 BioGenesis-ToT Chatbot")
+    chatbot = gr.Chatbot(label="BioGenesis Chatbot", height=500)
+    user_input = gr.Textbox(placeholder="Ask a biology question...", label="Your message")
+    clear = gr.Button("Clear Chat")
 
-"""
-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)",
-        ),
-    ],
-)
+    state = gr.State([])  # Keeps chat history
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+    user_input.submit(generate_response, [user_input, state], [chatbot, state])
+    clear.click(lambda: ([], []), None, [chatbot, state])
 
+demo.launch(share=True)
 
-if __name__ == "__main__":
-    demo.launch()