| # 24GiB | |
| pip install "transformers==4.51.*" | |
| CUDA_VISIBLE_DEVICES=0 \ | |
| swift sft \ | |
| --model OpenGVLab/InternVL3-8B \ | |
| --dataset 'AI-ModelScope/LaTeX_OCR:human_handwrite#20000' \ | |
| --load_from_cache_file true \ | |
| --split_dataset_ratio 0.01 \ | |
| --tuner_type lora \ | |
| --torch_dtype bfloat16 \ | |
| --num_train_epochs 1 \ | |
| --per_device_train_batch_size 1 \ | |
| --per_device_eval_batch_size 1 \ | |
| --learning_rate 1e-4 \ | |
| --lora_rank 8 \ | |
| --lora_alpha 32 \ | |
| --target_modules all-linear \ | |
| --freeze_vit true \ | |
| --gradient_accumulation_steps 16 \ | |
| --eval_steps 50 \ | |
| --save_steps 50 \ | |
| --save_total_limit 2 \ | |
| --logging_steps 5 \ | |
| --max_length 4096 \ | |
| --output_dir output \ | |
| --warmup_ratio 0.05 \ | |
| --dataset_num_proc 4 \ | |
| --dataloader_num_workers 4 | |