import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, TrainingArguments, Trainer
from peft import LoraConfig, get_peft_model

model_id = "mistralai/Mistral-7B-Instruct-v0.2"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    load_in_4bit=True,
    device_map="auto"
)

lora_config = LoraConfig(
    r=8,
    lora_alpha=16,
    target_modules=["q_proj", "v_proj"],
    lora_dropout=0.05,
    task_type="CAUSAL_LM"
)

model = get_peft_model(model, lora_config)

def tokenize(batch):
    return tokenizer(batch["text"], truncation=True, padding="max_length", max_length=256)

dataset = dataset.map(tokenize, batched=True)

args = TrainingArguments(
    output_dir="./lora-output",
    per_device_train_batch_size=1,
    gradient_accumulation_steps=4,
    num_train_epochs=1,
    fp16=True,
    logging_steps=10,
    save_strategy="epoch"
)

trainer = Trainer(
    model=model,
    args=args,
    train_dataset=dataset
)

trainer.train()