Instructions to use marin-dna/tokenizer-char-bos-eos with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use marin-dna/tokenizer-char-bos-eos with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("marin-dna/tokenizer-char-bos-eos", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "version": "1.0", | |
| "truncation": null, | |
| "padding": null, | |
| "added_tokens": [ | |
| { | |
| "id": 0, | |
| "content": "[PAD]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 1, | |
| "content": "[UNK]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 2, | |
| "content": "[BOS]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 3, | |
| "content": "[EOS]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| } | |
| ], | |
| "normalizer": { | |
| "type": "Lowercase" | |
| }, | |
| "pre_tokenizer": { | |
| "type": "Split", | |
| "pattern": { | |
| "Regex": ".{1}" | |
| }, | |
| "behavior": "Isolated", | |
| "invert": false | |
| }, | |
| "post_processor": { | |
| "type": "TemplateProcessing", | |
| "single": [ | |
| { | |
| "SpecialToken": { | |
| "id": "[BOS]", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "SpecialToken": { | |
| "id": "[EOS]", | |
| "type_id": 0 | |
| } | |
| } | |
| ], | |
| "pair": [ | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "B", | |
| "type_id": 1 | |
| } | |
| } | |
| ], | |
| "special_tokens": { | |
| "[BOS]": { | |
| "id": "[BOS]", | |
| "ids": [ | |
| 2 | |
| ], | |
| "tokens": [ | |
| "[BOS]" | |
| ] | |
| }, | |
| "[EOS]": { | |
| "id": "[EOS]", | |
| "ids": [ | |
| 3 | |
| ], | |
| "tokens": [ | |
| "[EOS]" | |
| ] | |
| } | |
| } | |
| }, | |
| "decoder": { | |
| "type": "Fuse" | |
| }, | |
| "model": { | |
| "type": "WordLevel", | |
| "vocab": { | |
| "[PAD]": 0, | |
| "[UNK]": 1, | |
| "[BOS]": 2, | |
| "[EOS]": 3, | |
| "a": 4, | |
| "c": 5, | |
| "g": 6, | |
| "t": 7 | |
| }, | |
| "unk_token": "[UNK]" | |
| } | |
| } |