Instructions to use microsoft/xdoc-base-websrc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/xdoc-base-websrc with Transformers:
# Load model directly from transformers import AutoTokenizer, Layoutlmv1ForQuestionAnswering_roberta tokenizer = AutoTokenizer.from_pretrained("microsoft/xdoc-base-websrc") model = Layoutlmv1ForQuestionAnswering_roberta.from_pretrained("microsoft/xdoc-base-websrc", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "add_prefix_space": false, | |
| "bos_token": { | |
| "__type": "AddedToken", | |
| "content": "<s>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "cls_token": { | |
| "__type": "AddedToken", | |
| "content": "<s>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "eos_token": { | |
| "__type": "AddedToken", | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "errors": "replace", | |
| "full_tokenizer_file": null, | |
| "mask_token": { | |
| "__type": "AddedToken", | |
| "content": "<mask>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "model_max_length": 512, | |
| "name_or_path": "/ssddata/jzhaaa/Projects/jingye/resource/azcopy_linux_amd64_10.16.1/step-540000", | |
| "pad_token": { | |
| "__type": "AddedToken", | |
| "content": "<pad>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "sep_token": { | |
| "__type": "AddedToken", | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "special_tokens_map_file": "/mnt/workspace/uniform_combine_all/output_dir/output/[0522_final]roberta-base-big-model/step-440000/special_tokens_map.json", | |
| "tokenizer_class": "RobertaTokenizer", | |
| "unk_token": { | |
| "__type": "AddedToken", | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |