Update app.py

app.py

@@ -1,23 +1,21 @@
 from flask import Flask, request, jsonify
 from transformers import AutoTokenizer, AutoModelForCausalLM
-from peft import PeftModel
 import torch
 
 app = Flask(__name__)
 
-BASE_MODEL  = "Qwen/Qwen2.5-0.5B-Instruct"
-ADAPTER     = "newtechdevng/math-tutor-smollm2-360M"  # your HF repo
+MODEL_ID = "newtechdevng/math-tutor-smollm2-360M"  # full model, load directly
 
 SYSTEM_PROMPT = "You are a helpful math assistant."
 
 print("Loading model...")
-tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)
-base_model = AutoModelForCausalLM.from_pretrained(
-    BASE_MODEL,
-    torch_dtype=torch.float32,
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    dtype=torch.float32,
     device_map="auto"
 )
-model = PeftModel.from_pretrained(base_model, ADAPTER)
 model.eval()
 print("✅ Model ready!")
 
@@ -50,11 +48,9 @@ def generate():
             **inputs,
             max_new_tokens=max_new_tokens,
             do_sample=False,
-            temperature=1.0,
             pad_token_id=tokenizer.eos_token_id,
         )
 
-    # Decode only the new tokens
     new_tokens = outputs[0][inputs["input_ids"].shape[1]:]
     answer = tokenizer.decode(new_tokens, skip_special_tokens=True)