from transformers import AutoModelForCausalLM, BitsAndBytesConfig, AutoTokenizer
import torch

MODEL_NAME = "Sakuna/LLaMaCoderAll"
device = "cuda:0"


bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.float16,
)

model = AutoModelForCausalLM.from_pretrained(
    MODEL_NAME,
    quantization_config=bnb_config,
    trust_remote_code=True
)

tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True)
tokenizer.pad_token = tokenizer.eos_token

model = model.to(device)
model.eval()

prompt = "Write a Java program to calculate the factorial of a given number k"
input = f"{prompt}\n### Solution:\n"
device = "cuda:0"

inputs = tokenizer(input, return_tensors="pt").to(device)
outputs = model.generate(**inputs, max_length=256, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))