Views
No views yet
transformers/csarron/bert-base-uncased-squad-v1,
converted to Lucid-native safetensors.| Tag | exact_match | f1 | Params | GFLOPs | Size | Source |
|---|---|---|---|---|---|---|
SQUAD_V1 (default) | 80.9 | 88.1 | 109.5M | — | 417.67 MB | transformers |
1import lucid
2import lucid.models as models
3from lucid.models.weights import BERTBaseQAWeights
4
5# default tag
6model = models.bert_base_qa(pretrained=True)
7
8# explicit tag (enum or string)
9model = models.bert_base_qa(weights=BERTBaseQAWeights.SQUAD_V1)
10model = models.bert_base_qa(pretrained="SQUAD_V1")
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)
15start, end = out.start_logits, out.end_logits # (B, T) eachtransformers/csarron/bert-base-uncased-squad-v1 via
python -m tools.convert_weights bert_base_qa --tag SQUAD_V1.
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.