SAVRN
Search Contact SAVRN

Open-weight model

jina-bert-flash-implementation

by Jina AI jinaai/jina-bert-flash-implementation

To run the model on GPU, you need to install Flash Attention. You may either install from pypi (which may not work with fused-dense), or from source. To install from source, clone the GitHub repository: The code provided here should work with commit 43950dd.

Parameters
Context
Weights144.3 KB
License
AccessOpen weights
Monthly Downloads887.7k

Model Card

To run the model on GPU, you need to install Flash Attention. You may either install from pypi (which may not work with fused-dense), or from source. To install from source, clone the GitHub repository: The code provided here should work with commit 43950dd. Change to the cloned repo and install: This will compile the flash-attention kernel, which will take some time. If you would like to use fused MLPs (e.g. to use activation checkpointing), you may install fused-dense also from source: The config adds some new parameters: - useflashattn: If True, always use flash attention. If None, use flash attention when GPU is available. If False, never use flash attention (works on CPU).…

Excerpt from the card by Jina AI.

Configuration

Layers
12
Hidden size
768
Feed-forward size
3,072
Attention heads
12
Vocabulary size
30,528
Stored precision
float16
Model type
bert

Identity and Version

Repository
jinaai/jina-bert-flash-implementation
Publisher
Jina AI
Task
Not stated by the source
Modality
Other
Library
transformers
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
b78d1595de294f13ffe7b19d6cd63892a6e4e7a4
First published
2024-02-21
Last updated
2024-05-31

Files and Weights

12 files, 144.3 KB in total.

Configuration11 files · 142.4 KB
Documentation1 file · 1.9 KB
Every file
FileTypeSizeSHA-256
bert_padding.pyConfiguration9.8 KB
block.pyConfiguration17.4 KB
config.jsonConfiguration1.2 KB
configuration_bert.pyConfiguration5.8 KB
convert_v2_weights.pyConfiguration6.1 KB
embedding.pyConfiguration2.3 KB
mha.pyConfiguration35.4 KB
mlp.pyConfiguration8.0 KB
modeling_bert.pyConfiguration33.4 KB
modeling_for_glue.pyConfiguration10.7 KB
modeling_lora.pyConfiguration12.3 KB
README.mdDocumentation1.9 KB

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download from Jina AI

Released by Jina AI through its official repository on Hugging Face.