Update app.py

app.py

@@ -1,6 +1,6 @@
 from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel
-from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+from transformers import AutoTokenizer, AutoModelForCausalLM
 from huggingface_hub import login
 import os
 import torch
@@ -16,20 +16,12 @@ app = FastAPI(
 
 model_name = "google/gemma-3-270m"
 
-bnb_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=torch.bfloat16
-)
-
 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
-    quantization_config=bnb_config,
     device_map="auto",
     trust_remote_code=True,
-    torch_dtype=torch.bfloat16
+    torch_dtype=torch.float16
 )
 model.eval()
 
@@ -57,7 +49,7 @@ async def generate_text(request: GenerateRequest):
         
         return {"generated_text": generated_text}
     except Exception as e:
-        raise HTTPException(status_code=500, detail=f"VexaAI-Lab: Ошибка генерации: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"VexaAI-Lab: HTTP/S error: {str(e)}")
 
 @app.get("/")
 async def root():