Update README.md

README.md

@@ -79,7 +79,18 @@ Use the code below to get started with the model.
 ### Training Procedure
 
 ```bash
- accelerate launch  --config_file examples/accelerate_configs/multi_gpu.yaml  examples/scripts/dpo_vlm.py    --dataset_name HuggingFaceH4/rlaif-v_formatted     --model_name_or_path HuggingFaceTB/SmolVLM-Instruct     --per_device_train_batch_size 8   --gradient_accumulation_steps 32     --dataset_num_proc 32     --output_dir dpo_smolvlm_rlaif-v     --bf16     --torch_dtype bfloat16      --use_peft    --lora_target_modules=all-linear exit
+accelerate launch  --config_file examples/accelerate_configs/multi_gpu.yaml \
+  examples/scripts/dpo_vlm.py \
+  --dataset_name HuggingFaceH4/rlaif-v_formatted \
+  --model_name_or_path HuggingFaceTB/SmolVLM-Instruct \
+  --per_device_train_batch_size 8 \
+  --gradient_accumulation_steps 32 \
+  --dataset_num_proc 32 \
+  --output_dir dpo_smolvlm_rlaif-v \
+  --bf16 \
+  --torch_dtype bfloat16 \
+  --use_peft \
+  --lora_target_modules=all-linear exit
 ```
 
 ### Framework versions