from transformers import BitsAndBytesConfig import torch from transformers import AutoModelForImageTextToText, AutoTokenizer, AutoProcessor from qwen_vl_utils import process_vision_info bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type='nf4', ) # processor = AutoProcessor.from_pretrained("google/gemma-3-270m") model = AutoModelForImageTextToText.from_pretrained( "Qwen/Qwen3-VL-30B-A3B-Instruct", torch_dtype=torch.bfloat16, device_map="auto"#, quantization_config=bnb_config ) from peft import LoraConfig, get_peft_model peft_config = LoraConfig( lora_alpha=16, lora_dropout=0.0, r=16, bias="none", task_type="CAUSAL_LM", target_modules=[ "q_proj", "k_proj", "v_proj", "o_proj", ] ) from trl import SFTConfig training_args = SFTConfig( output_dir="qwen_anti_aesthetics_3b", num_train_epochs=5, per_device_train_batch_size=4, per_device_eval_batch_size=4, gradient_accumulation_steps=2, gradient_checkpointing_kwargs={"use_reentrant": False}, max_length=None, optim="adamw_torch_fused", learning_rate=2e-5, weight_decay=0.001, logging_steps=10, eval_steps=500, logging_strategy="steps", eval_strategy="steps", save_strategy="steps", save_steps=500, bf16=True, warmup_ratio=0.02, push_to_hub=True, report_to="wandb", remove_unused_columns=False, dataloader_num_workers=12, dataloader_prefetch_factor=4, dataloader_pin_memory=True, completion_only_loss=True, lr_scheduler_type="cosine", ) trainer = SFTTrainer( model=model, peft_config=peft_config, args=training_args, train_dataset=train_ds, eval_dataset=test_ds, )