Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
jinaai
/
jina-bert-flash-implementation
like
4
Follow
Jina AI
354
Transformers
bert
custom_code
Inference Endpoints
🇪🇺 Region: EU
Model card
Files
Files and versions
Community
18
Train
Deploy
Use this model
refs/pr/14
jina-bert-flash-implementation
6 contributors
History:
96 commits
Markus28
wrap every layer in a checkpoint
e0da4c5
9 months ago
bert_padding.py
Safe
9.78 kB
reference the flash attention GitHub
9 months ago
block.py
Safe
17.4 kB
reference the flash attention GitHub
9 months ago
configuration_bert.py
Safe
5.82 kB
feat: make num of loras part of the config
9 months ago
embedding.py
Safe
2.26 kB
clean up embeddings.py (#7)
9 months ago
mha.py
Safe
35.3 kB
reference the flash attention GitHub
9 months ago
mlp.py
Safe
6.17 kB
reference the flash attention GitHub
9 months ago
modeling_bert.py
Safe
33.6 kB
wrap every layer in a checkpoint
9 months ago
modeling_for_glue.py
Safe
10.7 kB
feat: assert return_dict
9 months ago
modeling_lora.py
Safe
10.4 kB
fix: fixed from_bert method
9 months ago
tokenizer.py
Safe
4.42 kB
Update tokenizer.py
9 months ago
