↓ 2 callersMethodprepare_inputs_labels_for_multimodal(
self, input_ids, position_ids, attention_mask, past_key_values, labels,
images, image_sizes=
bmf/demo/fast_caption_module/convert/llava_py/llava/model/llava_arch.py:145
↓ 2 callersMethodprocess_image(self, image, image_process_mode, return_pil=False, image_format='PNG', max_len=1344, min_len=672)
bmf/demo/fast_caption_module/convert/llava_py/llava/conversation.py:112