wandb/sourcecode-detection

1{2  "add_prefix_space": false,3  "added_tokens_decoder": {4    "0": {5      "content": "<s>",6      "lstrip": false,7      "normalized": true,8      "rstrip": false,9      "single_word": false,10      "special": true11    },12    "1": {13      "content": "<pad>",14      "lstrip": false,15      "normalized": true,16      "rstrip": false,17      "single_word": false,18      "special": true19    },20    "2": {21      "content": "</s>",22      "lstrip": false,23      "normalized": true,24      "rstrip": false,25      "single_word": false,26      "special": true27    },28    "3": {29      "content": "<unk>",30      "lstrip": false,31      "normalized": true,32      "rstrip": false,33      "single_word": false,34      "special": true35    },36    "4": {37      "content": "<mask>",38      "lstrip": true,39      "normalized": false,40      "rstrip": false,41      "single_word": false,42      "special": true43    }44  },45  "bos_token": "<s>",46  "clean_up_tokenization_spaces": false,47  "cls_token": "<s>",48  "eos_token": "</s>",49  "errors": "replace",50  "mask_token": "<mask>",51  "max_len": 512,52  "max_length": 512,53  "model_max_length": 512,54  "pad_token": "<pad>",55  "sep_token": "</s>",56  "tokenizer_class": "RobertaTokenizer",57  "trim_offsets": true,58  "truncation": true,59  "unk_token": "<unk>"60}61