Update app.py

app.py

@@ -1,70 +1,69 @@
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
 import gradio as gr
-from huggingface_hub import InferenceClient
 
+# --- Models Load (CPU ke liye optimized) ---
+BASE_MODEL = "Qwen/Qwen2.5-1.5B"
+LORA_ADAPTER = "modular-ai/qwen"
 
-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")
+print("Loading base model on CPU... (ye 1-2 min lagega pehli baar)")
 
-    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
+base_model = AutoModelForCausalLM.from_pretrained(
+    BASE_MODEL,
+    torch_dtype=torch.float32,      # CPU pe float16 nahi chalta
+    device_map="cpu",               # Sirf CPU
+    trust_remote_code=True,
+    low_cpu_mem_usage=True          # Memory bachaye
+)
 
-        response += token
-        yield response
+print("Loading LoRA adapter...")
+model = PeftModel.from_pretrained(base_model, LORA_ADAPTER)
 
+tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL, trust_remote_code=True)
+if tokenizer.pad_token is None:
+    tokenizer.pad_token = tokenizer.eos_token
 
-"""
-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)",
-        ),
-    ],
-)
+# --- Chat Function (Fast & Safe) ---
+def ask_kant(message, history):
+    prompt = f"### Instruction: You are Immanuel Kant.\n\n### Input: {message}\n\n### Response:"
+    inputs = tokenizer(prompt, return_tensors="pt", truncation=True, max_length=512)
+    
+    with torch.no_grad():
+        output = model.generate(
+            **inputs,
+            max_new_tokens=200,
+            temperature=0.7,
+            do_sample=True,
+            top_p=0.9,
+            repetition_penalty=1.1,
+            pad_token_id=tokenizer.eos_token_id
+        )
+    
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    bot_reply = response.split("### Response:")[-1].strip()
+    return bot_reply
 
+# --- Gradio UI (Simple & Fast) ---
 with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+    gr.Markdown("# 🧠 **Kant AI** – Qwen2.5-1.5B LoRA")
+    gr.Markdown("**Zero GPU | Free | Live Demo**  \nPoochein koi bhi sawal, *Immanuel Kant* jawab denge!")
 
+    chatbot = gr.ChatInterface(
+        fn=ask_kant,
+        title="",
+        examples=[
+            "What is freedom?",
+            "Kya hai swatantrata?",
+            "Explain categorical imperative",
+            "Moral law kya hai?"
+        ],
+        cache_examples=False,
+        submit_btn="Ask Kant",
+        retry_btn=None,
+        clear_btn="Clear"
+    )
+    
+    gr.Markdown("---\n*Model: Qwen2.5-1.5B + LoRA | CPU Only | ~8-12 sec per reply*")
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()