Update main.py

main.py

@@ -1,32 +1,24 @@
 from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel
 import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import json
 
 app = FastAPI()
 
 MODEL_ID = "Qwen/Qwen2.5-1.5B-Instruct"
 
-print(f"[Wave] Загрузка модели {MODEL_ID} с квантированием NF4...")
-
-# ========== NF4 КВАНТИРОВАНИЕ ==========
-bnb_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=torch.float16,
-    bnb_4bit_use_double_quant=True
-)
+print(f"[Wave] Загрузка модели {MODEL_ID} (FP16)...")
 
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
-    quantization_config=bnb_config,
+    torch_dtype=torch.float16,
     device_map="auto",
     low_cpu_mem_usage=True
 )
 
-print("[Wave] Модель загружена в NF4!")
+print("[Wave] Модель загружена в FP16!")
 
 class GenerateRequest(BaseModel):
     prompt: str
@@ -40,7 +32,7 @@ class ChatRequest(BaseModel):
 
 @app.get("/")
 def root():
-    return {"status": "Wave AI is alive!", "model": MODEL_ID, "quant": "NF4"}
+    return {"status": "Wave AI is alive!", "model": MODEL_ID, "quant": "FP16"}
 
 @app.post("/generate")
 def generate(req: GenerateRequest):