Update app.py

app.py

@@ -13,8 +13,9 @@ st.write("This AI tutor is fine-tuned on Python-related questions.")
 model_name = "microsoft/phi-2"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-# 🔥 Fix: Add padding token
-tokenizer.add_special_tokens({'pad_token': '[PAD]'})
+# 🔥 Fix: Add padding token if missing
+if tokenizer.pad_token is None:
+    tokenizer.add_special_tokens({'pad_token': '[PAD]'})
 
 # Check if fine-tuned model exists
 model_path = "./models"
@@ -27,7 +28,7 @@ else:
     # Load model on CPU
     model = AutoModelForCausalLM.from_pretrained(
         model_name,
-        torch_dtype=torch.bfloat16,
+        torch_dtype=torch.float32,  # Use float32 for CPU compatibility
         device_map={"": "cpu"}  # Force CPU usage
     )
 
@@ -45,13 +46,13 @@ else:
     )
     model = get_peft_model(model, lora_config)
 
-    # Load dataset
-    dataset = load_dataset("mbpp", split="train")
+    # Load dataset (Choose any one)
+    dataset = load_dataset("lvwerra/codeparrot-clean", split="train")  # ✅ Free dataset
 
     # 🔥 Fix: Set `labels` properly
     def tokenize_function(examples):
-        inputs = tokenizer(examples["text"], padding="max_length", truncation=True, max_length=512)
-        inputs["labels"] = inputs["input_ids"].copy()  # ✅ Fix: Ensure labels exist
+        inputs = tokenizer(examples["content"], padding="max_length", truncation=True, max_length=512)
+        inputs["labels"] = inputs["input_ids"].copy()  # ✅ Ensure labels exist
         return inputs
 
     tokenized_dataset = dataset.map(tokenize_function, batched=True)
@@ -69,8 +70,8 @@ else:
         logging_dir="./logs",
         logging_steps=10,
         save_total_limit=2,
-        evaluation_strategy="no",  # ✅ Fix: No evaluation dataset needed
-        load_best_model_at_end=False  # ✅ Fix: Prevents conflict with no eval dataset
+        evaluation_strategy="no",  # ✅ No eval dataset needed
+        load_best_model_at_end=False  # ✅ Prevents conflicts
     )
 
     # Trainer