Create app.py

app.py

@@ -0,0 +1,82 @@
+import gradio as gr
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+from peft import PeftModel
+from threading import Thread
+
+BASE_MODEL = "Qwen/Qwen3-0.6B"
+ADAPTER_ID = "Redhanuman/Shadow-0.7B"
+
+print("🌑 Loading Shadow Brain...")
+tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)
+
+base_model = AutoModelForCausalLM.from_pretrained(
+    BASE_MODEL,
+    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+    device_map="auto"
+)
+
+model = PeftModel.from_pretrained(base_model, ADAPTER_ID)
+model.eval()
+
+def predict(message, history):
+    system_prompt = (
+        "You are Shadow 0.7B, a reasoning AI created by Aman Kumar Pandey. "
+        "Use <think> tags to plan logic before answering."
+    )
+    
+    messages = [{"role": "system", "content": system_prompt}]
+    for user_msg, bot_msg in history:
+        messages.append({"role": "user", "content": user_msg})
+        messages.append({"role": "assistant", "content": bot_msg})
+    messages.append({"role": "user", "content": message})
+
+    input_ids = tokenizer.apply_chat_template(
+        messages,
+        tokenize=True,
+        add_generation_prompt=True,
+        return_tensors="pt"
+    ).to(model.device)
+
+    streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+    generation_kwargs = dict(
+        input_ids=input_ids,
+        streamer=streamer,
+        max_new_tokens=1024,
+        temperature=0.7,
+        top_p=0.9,
+        repetition_penalty=1.1,
+    )
+
+    thread = Thread(target=model.generate, kwargs=generation_kwargs)
+    thread.start()
+
+    partial_message = ""
+    for new_token in streamer:
+        partial_message += new_token
+        yield partial_message
+
+custom_css = """
+body { background-color: #0b0f19; color: #e0e0e0; }
+gradio-app { background-color: #0b0f19; }
+.message.user { border-color: #3b82f6 !important; background: #1e293b !important; }
+.message.bot { border-color: #8b5cf6 !important; background: #0f172a !important; }
+h1 { color: #f8fafc; font-family: 'Inter', sans-serif; font-weight: 800; }
+footer { display: none !important; }
+"""
+
+with gr.Blocks(theme=gr.themes.Base(), css=custom_css) as demo:
+    gr.Markdown("# 🌑 Shadow 0.7B")
+    gr.Markdown("Created by **Aman Kumar Pandey** | Focused on Code Logic & Reasoning")
+    
+    chat = gr.ChatInterface(
+        fn=predict,
+        retry_btn=None,
+        undo_btn=None,
+        clear_btn="🗑️ Clear Memory",
+        examples=[
+            "Write a Python function to check for palindromes.", 
+            "If I have 3 apples and eat one, how many do I have?"
+        ],
+    )
+demo.queue().launch()