kuleshov-group
/

caduceus-ps_seqlen-1k_d_model-256_n_layer-4_lr-8e-3

Model card Files Files and versions Community

caduceus-ps_seqlen-1k_d_model-256_n_layer-4_lr-8e-3 / modeling_caduceus.py

Commit History

Ensure weights are tied for BiMamba (if applicable) when loaded from_pretrained

cafe1ed
verified

yairschiff commited on Nov 26, 2024

Enable mambav2 compat

bca66b0
verified

yairschiff commited on Oct 7, 2024

Update modeling_caduceus.py

c6109d3
verified

yairschiff commited on Jun 11, 2024

Upload CaduceusForMaskedLM

6a5edc5
verified

yairschiff commited on Apr 16, 2024