Instructions to use timodonnell/protein-docs-all-doc-types-tokenizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use timodonnell/protein-docs-all-doc-types-tokenizer with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("timodonnell/protein-docs-all-doc-types-tokenizer", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<pad>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "<eos>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "2839": { | |
| "content": "<UNK>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<eos>", | |
| "extra_special_tokens": {}, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "<pad>", | |
| "tokenizer_class": "PreTrainedTokenizerFast", | |
| "unk_token": "<UNK>" | |
| } | |