Hi, I was running the colab notebook provided in this blog, I am getting this error:
/tmp/ipython-input-1538314790.py in <cell line: 0>()
----> 1 trainer = SFTTrainer(
2 model=model,
3 args=training_args,
4 data_collator=collate_fn,
5 train_dataset=dataset["train"],
/usr/local/lib/python3.12/dist-packages/trl/trainer/sft_trainer.py in __init__(self, model, args, data_collator, train_dataset, eval_dataset, processing_class, compute_loss_func, compute_metrics, callbacks, optimizers, optimizer_cls_and_kwargs, preprocess_logits_for_metrics, peft_config, formatting_func)
807 self._is_vision_dataset = "image" in dataset_sample or "images" in dataset_sample
808 if self._is_vision_dataset and not self._is_vlm:
--> 809 raise ValueError(
810 "The dataset appears to be vision-related (contains 'image' or 'images' keys), but the provided "
811 "model does not seem to be a vision-language model. Please check your model and dataset."
ValueError: The dataset appears to be vision-related (contains 'image' or 'images' keys), but the provided model does not seem to be a vision-language model. Please check your model and dataset.
