Views
No views yet
small_bert/bert_en_uncased_L-4_H-256_A-4/2)
Framework: TensorFlow
Language: English0: Advertising/General Content1: Insider Recruitment ActivityBertTokenizer from bert-base-uncasedsmall_bert/bert_en_uncased_L-4_H-256_A-4/2 from TensorFlow Hubsmall_bert checkpoints were pretrained on the
same vocabulary as bert-base-uncased. Token IDs and special tokens
([CLS], [SEP], [PAD]) are therefore aligned, and the Hugging Face
tokenizer can be used directly with the TF Hub encoder without a
vocabulary mismatch.bert-base-uncased tokenizer and the TF Hub small_bert vocabulary:1token HF TFHub
2 [PAD] 0 0
3 [UNK] 100 100
4 [CLS] 101 101
5 [SEP] 102 102
6 [MASK] 103 103
7 recruiting HF=[14357] TFHub=[14357] OK
8 insider HF=[25297] TFHub=[25297] OK
9 telegram HF=[23921] TFHub=[23921] OK
10 threat HF=[5081] TFHub=[5081] OK
11 exfiltration HF=[4654, 28674] TFHub=[4654, 28674] OK
12 forum HF=[7057] TFHub=[7057] OK
13
14vocab size match: True | specials match: True | samples match: True
15SAFE TO ASSERT: Truebert-base-uncased)1@software{synshade2026,
2 title={SynShade: Insider Threat Detection in Dark Web Communications},
3 author={[Wong Hau Pepelu]},
4 year={2026},
5 url={https://huggingface.co/wong-hau-pepelu/synshade-insider-threat-detector}
6}