Instructions to use cctien/protein_bpe_64 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cctien/protein_bpe_64 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("cctien/protein_bpe_64", 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": "[s]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 3, | |
| "content": "[/s]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 4, | |
| "content": "[m]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 5, | |
| "content": "[/m]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| } | |
| ], | |
| "normalizer": null, | |
| "pre_tokenizer": { | |
| "type": "Split", | |
| "pattern": { | |
| "Regex": "(\\[pad\\]|\\[unk\\]|\\[s\\]|\\[/s\\]|\\[m\\]|\\[/m\\])" | |
| }, | |
| "behavior": "Isolated", | |
| "invert": false | |
| }, | |
| "post_processor": { | |
| "type": "TemplateProcessing", | |
| "single": [ | |
| { | |
| "SpecialToken": { | |
| "id": "[s]", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "SpecialToken": { | |
| "id": "[/s]", | |
| "type_id": 0 | |
| } | |
| } | |
| ], | |
| "pair": [ | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "B", | |
| "type_id": 1 | |
| } | |
| } | |
| ], | |
| "special_tokens": { | |
| "[/s]": { | |
| "id": "[/s]", | |
| "ids": [ | |
| 3 | |
| ], | |
| "tokens": [ | |
| "[/s]" | |
| ] | |
| }, | |
| "[s]": { | |
| "id": "[s]", | |
| "ids": [ | |
| 2 | |
| ], | |
| "tokens": [ | |
| "[s]" | |
| ] | |
| } | |
| } | |
| }, | |
| "decoder": null, | |
| "model": { | |
| "type": "BPE", | |
| "dropout": null, | |
| "unk_token": null, | |
| "continuing_subword_prefix": null, | |
| "end_of_word_suffix": null, | |
| "fuse_unk": false, | |
| "byte_fallback": false, | |
| "ignore_merges": false, | |
| "vocab": { | |
| "[pad]": 0, | |
| "[unk]": 1, | |
| "[s]": 2, | |
| "[/s]": 3, | |
| "[m]": 4, | |
| "[/m]": 5, | |
| "A": 6, | |
| "B": 7, | |
| "C": 8, | |
| "D": 9, | |
| "E": 10, | |
| "F": 11, | |
| "G": 12, | |
| "H": 13, | |
| "I": 14, | |
| "K": 15, | |
| "L": 16, | |
| "M": 17, | |
| "N": 18, | |
| "O": 19, | |
| "P": 20, | |
| "Q": 21, | |
| "R": 22, | |
| "S": 23, | |
| "T": 24, | |
| "U": 25, | |
| "V": 26, | |
| "W": 27, | |
| "X": 28, | |
| "Y": 29, | |
| "Z": 30, | |
| "LL": 31, | |
| "AA": 32, | |
| "AL": 33, | |
| "GG": 34, | |
| "VL": 35, | |
| "GL": 36, | |
| "EL": 37, | |
| "SL": 38, | |
| "AV": 39, | |
| "IL": 40, | |
| "AG": 41, | |
| "RL": 42, | |
| "TL": 43, | |
| "DL": 44, | |
| "AE": 45, | |
| "KL": 46, | |
| "VV": 47, | |
| "SS": 48, | |
| "EE": 49, | |
| "AI": 50, | |
| "AR": 51, | |
| "KK": 52, | |
| "GV": 53, | |
| "GI": 54, | |
| "AD": 55, | |
| "AS": 56, | |
| "PL": 57, | |
| "AK": 58, | |
| "AT": 59, | |
| "GS": 60, | |
| "GK": 61, | |
| "FL": 62, | |
| "EI": 63 | |
| }, | |
| "merges": [ | |
| "L L", | |
| "A A", | |
| "A L", | |
| "G G", | |
| "V L", | |
| "G L", | |
| "E L", | |
| "S L", | |
| "A V", | |
| "I L", | |
| "A G", | |
| "R L", | |
| "T L", | |
| "D L", | |
| "A E", | |
| "K L", | |
| "V V", | |
| "S S", | |
| "E E", | |
| "A I", | |
| "A R", | |
| "K K", | |
| "G V", | |
| "G I", | |
| "A D", | |
| "A S", | |
| "P L", | |
| "A K", | |
| "A T", | |
| "G S", | |
| "G K", | |
| "F L", | |
| "E I" | |
| ] | |
| } | |
| } |