Update app.py

app.py

@@ -5,9 +5,9 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
 # =========================
-# MODEL YÜKLEME
+# AÇIK MODEL (GATED DEĞİL)
 # =========================
-MODEL_ID = "google/gemma-2b-it"
+MODEL_ID = "Qwen/Qwen2.5-0.5B-Instruct"
 
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 model = AutoModelForCausalLM.from_pretrained(
@@ -41,23 +41,20 @@ def root():
 
 @app.post("/api/chat")
 def chat(req: ChatReq):
-    prompt = f"Kullanıcı: {req.message}\nAsistan:"
+    prompt = f"<|user|>\n{req.message}\n<|assistant|>\n"
 
     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 
     with torch.no_grad():
         output = model.generate(
             **inputs,
-            max_new_tokens=200,
+            max_new_tokens=256,
             do_sample=True,
             temperature=0.7,
             top_p=0.9
         )
 
     text = tokenizer.decode(output[0], skip_special_tokens=True)
+    answer = text.split("<|assistant|>")[-1].strip()
 
-    # Asistan cevabını ayıkla
-    if "Asistan:" in text:
-        text = text.split("Asistan:")[-1].strip()
-
-    return {"response": text}
+    return {"response": answer}