nomic-ai/nomic-embed-text-v1.5
93614.3m
1{2 "added_tokens_decoder": {3 "0": {4 "content": "[PAD]",5 "lstrip": false,6 "normalized": false,7 "rstrip": false,8 "single_word": false,9 "special": true10 },11 "100": {12 "content": "[UNK]",13 "lstrip": false,14 "normalized": false,15 "rstrip": false,16 "single_word": false,17 "special": true18 },19 "101": {20 "content": "[CLS]",21 "lstrip": false,22 "normalized": false,23 "rstrip": false,24 "single_word": false,25 "special": true26 },27 "102": {28 "content": "[SEP]",29 "lstrip": false,30 "normalized": false,31 "rstrip": false,32 "single_word": false,33 "special": true34 },35 "103": {36 "content": "[MASK]",37 "lstrip": false,38 "normalized": false,39 "rstrip": false,40 "single_word": false,41 "special": true42 }43 },44 "clean_up_tokenization_spaces": true,45 "cls_token": "[CLS]",46 "do_lower_case": true,47 "mask_token": "[MASK]",48 "model_max_length": 8192,49 "pad_token": "[PAD]",50 "sep_token": "[SEP]",51 "strip_accents": null,52 "tokenize_chinese_chars": true,53 "tokenizer_class": "BertTokenizer",54 "unk_token": "[UNK]"55}56 