Update app.py

app.py

@@ -16,7 +16,6 @@ app = FastAPI(
 
 model_name = "google/gemma-3-270m"
 
-# Quantisation to 4-bit
 bnb_config = BitsAndBytesConfig(
     load_in_4bit=True,
     bnb_4bit_use_double_quant=True,
@@ -24,7 +23,6 @@ bnb_config = BitsAndBytesConfig(
     bnb_4bit_compute_dtype=torch.bfloat16
 )
 
-# Model loading.
 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
@@ -59,7 +57,7 @@ async def generate_text(request: GenerateRequest):
         
         return {"generated_text": generated_text}
     except Exception as e:
-        raise HTTPException(status_code=500, detail=f"VexaAI-Lab: HTTP/S error: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"VexaAI-Lab: Ошибка генерации: {str(e)}")
 
 @app.get("/")
 async def root():