from unsloth import FastVisionModel # FastLanguageModel for LLMs

model, tokenizer = FastVisionModel.from_pretrained(
    "unsloth/Qwen2-VL-7B-Instruct-bnb-4bit",
    load_in_4bit = True, # Use 4bit to reduce memory use. False for 16bit LoRA.
    use_gradient_checkpointing = "unsloth", # True or "unsloth" for long context
)

model = FastVisionModel.get_peft_model(
    model,
    finetune_vision_layers     = False, # False if not finetuning vision layers
    finetune_language_layers   = True, # False if not finetuning language layers
    finetune_attention_modules = True, # False if not finetuning attention layers
    finetune_mlp_modules       = True, # False if not finetuning MLP layers

    r = 16,           # The larger, the higher the accuracy, but might overfit
    lora_alpha = 16,  # Recommended alpha == r at least
    lora_dropout = 0,
    bias = "none",
    random_state = 3407,
    use_rslora = False,  # We support rank stabilized LoRA
    loftq_config = None, # And LoftQ
    # target_modules = "all-linear", # Optional now! Can specify a list if needed
)
from unsloth import is_bf16_supported
from unsloth.trainer import UnslothVisionDataCollator
from trl import SFTTrainer, SFTConfig

FastVisionModel.for_training(model)

trainer = SFTTrainer(
    model = model,
    tokenizer = tokenizer,
    data_collator = UnslothVisionDataCollator(model, tokenizer), # Must use!
    train_dataset = finetune_data,
    args = SFTConfig(
        per_device_train_batch_size = 1,
        gradient_accumulation_steps = 3,
        warmup_steps = 5,
        #max_steps = 30,
        num_train_epochs = 1, # Set this instead of max_steps for full training runs
        learning_rate = 2e-4,
        fp16 = not is_bf16_supported(),
        bf16 = is_bf16_supported(),
        logging_steps = 1,
        optim = "adamw_8bit",
        weight_decay = 0.01,
        lr_scheduler_type = "linear",
        seed = 3407,
        output_dir = "outputs",
        report_to = "none",     # For Weights and Biases

        # You MUST put the below items for vision finetuning:
        remove_unused_columns = False,
        dataset_text_field = "",
        dataset_kwargs = {"skip_prepare_dataset": True},
        dataset_num_proc = 4,
        max_seq_length = 2048,
    ),
)

trainer_stats = trainer.train()

model.save_pretrained("lora_model")  # Local saving
tokenizer.save_pretrained("lora_model")