MDDDDR/Ko-Luxia-8B-it-v0.1

# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("MDDDDR/Ko-Luxia-8B-it-v0.1")
model = AutoModelForCausalLM.from_pretrained(
    "MDDDDR/Ko-Luxia-8B-it-v0.1",
    device_map="auto",
    torch_dtype=torch.bfloat16
)

input_text = "사과가 뭐야?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))

bnd_config = BitsAndBytesConfig(
  load_in_4bit = True,
  bnb_4bit_use_double_quant = True,
  bnb_4bit_quant_type = 'nf4',
  bnb_4bit_compute_dtype = torch.bfloat16
)

lora_config = LoraConfig(
  r = 16,
  lora_alpha = 16,
  lora_dropout = 0.05,
  target_modules = ['gate_proj', 'up_proj', 'down_proj']
)