metadata
library_name: lucid
license: apache-2.0
tags:
- base
- bert
- lucid
datasets:
- wikipedia
- bookcorpus
pipeline_tag: feature-extraction
BERT-Tiny
Lucid port of transformers/google/bert_uncased_L-2_H-128_A-2,
converted to Lucid-native safetensors.
Available weights
| Tag | Params | GFLOPs | Size | Source |
|---|---|---|---|---|
WIKIPEDIA_BOOKSCORPUS (default) |
4.4M | — | 16.74 MB | transformers |
Usage
import lucid
import lucid.models as models
from lucid.models.weights import BertTinyWeights
# default tag
model = models.bert_tiny(pretrained=True)
# explicit tag (enum or string)
model = models.bert_tiny(weights=BertTinyWeights.WIKIPEDIA_BOOKSCORPUS)
model = models.bert_tiny(pretrained="WIKIPEDIA_BOOKSCORPUS")
# feed token ids (tokenize with the matching lucid.utils.tokenizer)
input_ids = lucid.tensor([[101, 7592, 2088, 102]], dtype=lucid.int64)
out = model(input_ids)
hidden = out.last_hidden_state # (B, T, hidden_size)
Conversion
Converted from transformers/google/bert_uncased_L-2_H-128_A-2 via
python -m tools.convert_weights bert_tiny --tag WIKIPEDIA_BOOKSCORPUS.
Key mapping + numerical parity verified against the source.
License
apache-2.0 — inherited from the original weights.
Citation
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.