Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
mosaicml
/
mosaic-bert-base-seqlen-256
like
2
Follow
Mosaic ML, Inc.
354
Fill-Mask
Transformers
PyTorch
c4
English
bert
custom_code
arxiv:
8 papers
License:
apache-2.0
Model card
Files
Files and versions
Community
1
Train
Deploy
Use this model
48ab7cc
mosaic-bert-base-seqlen-256
3 contributors
History:
6 commits
jacobfulano
Change attention_probs_dropout_prob to 0.1 so that triton FlashAttention dependencies are avoided
48ab7cc
11 months ago
.gitattributes
Safe
1.48 kB
initial commit
over 1 year ago
README.md
Safe
12.4 kB
Update README.md
over 1 year ago
bert_layers.py
Safe
47.3 kB
Upload BertForMaskedLM
over 1 year ago
bert_padding.py
Safe
6.26 kB
Upload BertForMaskedLM
over 1 year ago
config.json
Safe
843 Bytes
Change attention_probs_dropout_prob to 0.1 so that triton FlashAttention dependencies are avoided
11 months ago
configuration_bert.py
Safe
1.01 kB
Upload BertForMaskedLM
over 1 year ago
flash_attn_triton.py
Safe
42.7 kB
Upload BertForMaskedLM
over 1 year ago
pytorch_model.bin
Safe
pickle
Detected Pickle imports (3)
"torch.FloatStorage"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
What is a pickle import?
550 MB
LFS
Upload BertForMaskedLM
over 1 year ago
