| This does not | |
| apply to models leveraging the Encoder-Decoder framework. | |
| For image classification models, ([ViTForImageClassification]), the model expects a tensor of dimension | |
| (batch_size) with each value of the batch corresponding to the expected label of each individual image. | |
| For semantic segmentation models, ([SegformerForSemanticSegmentation]), the model expects a tensor of dimension | |
| (batch_size, height, width) with each value of the batch corresponding to the expected label of each individual pixel. | |
| For object detection models, ([DetrForObjectDetection]), the model expects a list of dictionaries with a | |
| class_labels and boxes key where each value of the batch corresponds to the expected label and number of bounding boxes of each individual image. | |
| For automatic speech recognition models, ([Wav2Vec2ForCTC]), the model expects a tensor of dimension (batch_size, | |
| target_length) with each value corresponding to the expected label of each individual token. | |
| Each model's labels may be different, so be sure to always check the documentation of each model for more information | |
| about their specific labels! | |
| The base models ([BertModel]) do not accept labels, as these are the base transformer models, simply outputting | |
| features. | |
| large language models (LLM) | |
| A generic term that refers to transformer language models (GPT-3, BLOOM, OPT) that were trained on a large quantity of data. |