Views
No views yet
transformers/dslim/bert-base-NER,
converted to Lucid-native safetensors.| Tag | f1 | Params | GFLOPs | Size | Source |
|---|---|---|---|---|---|
CONLL2003 (default) | 91.3 | 108.3M | — | 413.22 MB | transformers |
1import lucid
2import lucid.models as models
3from lucid.models.weights import BERTBaseNERWeights
4
5# default tag
6model = models.bert_base_token_cls(pretrained=True)
7
8# explicit tag (enum or string)
9model = models.bert_base_token_cls(weights=BERTBaseNERWeights.CONLL2003)
10model = models.bert_base_token_cls(pretrained="CONLL2003")
11
12# feed token ids (tokenize with the matching lucid.utils.tokenizer)
13input_ids = lucid.tensor([[101, 7592, 2088, 102]], dtype=lucid.int64)
14out = model(input_ids)
15logits = out.logits # classification logitstransformers/dslim/bert-base-NER via
python -m tools.convert_weights bert_base_token_cls --tag CONLL2003.
Key mapping + numerical parity verified against the source.mit — inherited from the original weights.Devlin et al., "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding", NAACL 2019. Miniatures: Turc et al., "Well-Read Students Learn Better", 2019.