Instructions to use microsoft/layoutlmv3-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/layoutlmv3-base with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("microsoft/layoutlmv3-base", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add TF weights
#3
by chriskoo - opened
Model converted by the transformers' pt_to_tf CLI. All converted model outputs and hidden layers were validated against its Pytorch counterpart.
Maximum crossload output difference=0.000e+00; Maximum crossload hidden layer difference=1.116e-04;
Maximum conversion output difference=0.000e+00; Maximum conversion hidden layer difference=1.116e-04;
👍 approved on my end, let's wait for the other reviews
P.S.: this is related to the following GH PR: https://github.com/huggingface/transformers/pull/18678 (adds TFLayoutLMv3)
LGTM, merging
nielsr changed pull request status to merged