[parser] support omegaconf (#7793)

examples/train_lora/llava1_5_lora_sft.yaml

@@ -1,45 +0,0 @@
-### model
-model_name_or_path: llava-hf/llava-1.5-7b-hf
-trust_remote_code: true
-
-### method
-stage: sft
-do_train: true
-finetuning_type: lora
-lora_rank: 8
-lora_target: all
-
-### dataset
-dataset: mllm_demo
-template: llava
-cutoff_len: 2048
-max_samples: 1000
-overwrite_cache: true
-preprocessing_num_workers: 16
-dataloader_num_workers: 4
-
-### output
-output_dir: saves/llava1_5-7b/lora/sft
-logging_steps: 10
-save_steps: 500
-plot_loss: true
-overwrite_output_dir: true
-save_only_model: false
-report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
-
-### train
-per_device_train_batch_size: 1
-gradient_accumulation_steps: 8
-learning_rate: 1.0e-4
-num_train_epochs: 3.0
-lr_scheduler_type: cosine
-warmup_ratio: 0.1
-bf16: true
-ddp_timeout: 180000000
-resume_from_checkpoint: null
-
-### eval
-# val_size: 0.1
-# per_device_eval_batch_size: 1
-# eval_strategy: steps
-# eval_steps: 500

examples/train_lora/qwen2vl_lora_dpo.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: Qwen/Qwen2-VL-7B-Instruct
+model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
 image_max_pixels: 262144
 video_max_pixels: 16384
 trust_remote_code: true

examples/train_lora/qwen2vl_lora_sft.yaml

@@ -1,5 +1,5 @@
 ### model
-model_name_or_path: Qwen/Qwen2-VL-7B-Instruct
+model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
 image_max_pixels: 262144
 video_max_pixels: 16384
 trust_remote_code: true