Update app.py

app.py

@@ -1,11 +1,11 @@
 import gradio as gr
 import torch
 from unsloth import FastLanguageModel
-import spaces # Ye line ZeroGPU ke liye zaroori hai
+import spaces # Ye ZeroGPU ke liye zaroori hai
 
 model_id = "anupbth1/Ved-Code-7B"
 
-# 1. Model loading (Global)
+# Model ko 4-bit mein load karna (RAM bachane ke liye)
 model, tokenizer = FastLanguageModel.from_pretrained(
     model_name = model_id,
     max_seq_length = 2048,
@@ -13,19 +13,22 @@ model, tokenizer = FastLanguageModel.from_pretrained(
 )
 FastLanguageModel.for_inference(model)
 
-# 2. GPU Function
-@spaces.GPU # Ye decorator model ko GPU power deta hai
-def generate_code(message, history):
+# ZeroGPU access ke liye decorator
+@spaces.GPU(duration=60)
+def generate(message, history):
     messages = [{"role": "user", "content": message}]
     inputs = tokenizer.apply_chat_template(
         messages,
         add_generation_prompt = True,
         return_tensors = "pt"
-    ).to("cuda") # Force to CUDA
+    ).to("cuda")
     
     outputs = model.generate(**inputs, max_new_tokens=512)
-    response = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
-    return response
+    return tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
 
-# 3. Chat Interface
-gr.ChatInterface(generate_code).launch()
+# UI Layout
+gr.ChatInterface(
+    generate, 
+    title="Ved-Code-7B 🚀",
+    description="Custom Coding Assistant by anupbth1"
+).launch()