Flashness123

Results 3 comments of Flashness123

use seed instead of random_state: train_test = toy_dataset.train_test_split(test_size=0.05, seed = 42)

@kirby707 Hey, have you found a solution yet?

@Veason-silverbullet Thank you, but I have developped a big finetuned donut model for extracting information from custom documents. Unfortunately the VisionEncoderDecoder is not good at ouputting any numbers. Does anyone...