Updated model with better training and evaluation. Test and val data included as pickle files. Older Legacy files were removed to avoid confusion.
f4e3085
| { | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<s>NOTUSED", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "<pad>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "2": { | |
| "content": "</s>NOTUSED", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "3": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "5": { | |
| "content": "<s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "6": { | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32004": { | |
| "content": "<mask>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "additional_special_tokens": [ | |
| "<s>NOTUSED", | |
| "</s>NOTUSED" | |
| ], | |
| "bos_token": "<s>", | |
| "clean_up_tokenization_spaces": true, | |
| "cls_token": "<s>", | |
| "eos_token": "</s>", | |
| "mask_token": "<mask>", | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "<pad>", | |
| "sep_token": "</s>", | |
| "sp_model_kwargs": {}, | |
| "tokenizer_class": "CamembertTokenizer", | |
| "unk_token": "<unk>" | |
| } | |