Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
jinaai
/
jina-bert-flash-implementation
like
2
Transformers
bert
custom_code
Inference Endpoints
๐ช๐บ Region: EU
Model card
Files
Files and versions
Community
18
Train
Deploy
Use this model
7771ce3
jina-bert-flash-implementation
6 contributors
History:
77 commits
Markus28
bwang0911
clean up embeddings.py (
#7
)
7771ce3
verified
6 months ago
bert_padding.py
9.78 kB
reference the flash attention GitHub
6 months ago
block.py
17.4 kB
reference the flash attention GitHub
6 months ago
configuration_bert.py
5.76 kB
added classifier dropout
6 months ago
embedding.py
2.26 kB
clean up embeddings.py (#7)
6 months ago
mha.py
35.3 kB
reference the flash attention GitHub
6 months ago
mlp.py
6.17 kB
reference the flash attention GitHub
6 months ago
modeling_bert.py
28.7 kB
feat: choose flash attention heuristically if not set explicitly
6 months ago
modeling_for_glue.py
10.7 kB
feat: assert return_dict
6 months ago
modeling_lora.py
8.31 kB
feat: return from_bert for from_pretrained
6 months ago
tokenizer.py
3.95 kB
support-fast-tokenizer (#6)
6 months ago