Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
quietflamingo
/
dnaberts-no-flashattention
like
0
PyTorch
bert
custom_code
arxiv:
2402.08777
License:
apache-2.0
Model card
Files
Files and versions
Community
1
main
dnaberts-no-flashattention
Ctrl+K
Ctrl+K
3 contributors
History:
7 commits
quietflamingo
Update README.md
f4d8065
verified
about 2 months ago
.gitattributes
Safe
1.52 kB
initial commit
over 1 year ago
README.md
Safe
1.06 kB
Update README.md
about 2 months ago
bert_layers.py
Safe
40.7 kB
Removed FlashAttention dependency.
about 2 months ago
bert_padding.py
Safe
6.1 kB
Upload 9 files
over 1 year ago
config.json
Safe
1.03 kB
Upload 9 files
over 1 year ago
configuration_bert.py
Safe
1.02 kB
Upload 9 files
over 1 year ago
flash_attn_triton.py
Safe
42.7 kB
Upload 9 files
over 1 year ago
pytorch_model.bin
Safe
pickle
Detected Pickle imports (3)
"collections.OrderedDict"
,
"torch.FloatStorage"
,
"torch._utils._rebuild_tensor_v2"
What is a pickle import?
468 MB
LFS
Upload 9 files
over 1 year ago
special_tokens_map.json
Safe
125 Bytes
Upload 9 files
over 1 year ago
tokenizer.json
Safe
168 kB
Upload 9 files
over 1 year ago
tokenizer_config.json
268 Bytes
Upload 9 files
over 1 year ago