Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
kuleshov-group
/
caduceus-ph_seqlen-131k_d_model-256_n_layer-16
like
6
Follow
Kuleshov Group
56
Fill-Mask
Transformers
Safetensors
caduceus
custom_code
arxiv:
2403.03234
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
2
Train
Use this model
main
caduceus-ph_seqlen-131k_d_model-256_n_layer-16
Ctrl+K
Ctrl+K
1 contributor
History:
13 commits
yairschiff
Ensure weights are tied for BiMamba (if applicable) when loaded from_pretrained
aa843f6
verified
7 months ago
.gitattributes
Safe
1.52 kB
initial commit
over 1 year ago
README.md
Safe
2.29 kB
Update README.md
over 1 year ago
config.json
Safe
1.38 kB
Upload CaduceusForMaskedLM
over 1 year ago
configuration_caduceus.py
Safe
1.96 kB
Upload CaduceusForMaskedLM
over 1 year ago
model.safetensors
Safe
30.9 MB
xet
Upload CaduceusForMaskedLM
over 1 year ago
modeling_caduceus.py
Safe
28.6 kB
Ensure weights are tied for BiMamba (if applicable) when loaded from_pretrained
7 months ago
modeling_rcps.py
Safe
9.98 kB
Enable mambav2 compat
8 months ago
special_tokens_map.json
Safe
173 Bytes
Upload tokenizer
over 1 year ago
tokenization_caduceus.py
Safe
4.97 kB
Upload tokenizer
over 1 year ago
tokenizer_config.json
Safe
1.49 kB
Upload tokenizer
over 1 year ago
