BRAVE or Swarms of Vision Transformers
Implementation of the paper: "BRAVE : Broadening the visual encoding of vision-language models". BRAVE achieves state-of-the-art performance on a broad range of captioning and VQA benchmarks and significantly reduces the aforementioned issues of VLMs, while requiring a smaller number of trainable parameters than existing methods and having a more compressed representation.
install
pip3 install brave-torch
usage
import torch
from brave_torch.main import SwarmOfViTs
# IMG Tensor
x = torch.randn(1, 3, 224, 224)
# Model
model = SwarmOfViTs(
image_size=224,
patch_size=32,
encoder_dim=512,
encoder_depth=6,
encoder_heads=8,
num_of_vits=4
)
# Forward
out = model(x)
print(out)
Citations
Todo
- Citation link
- Citation Bibtex
- Diagram photo
- Implement Andromeda Base LLM architecture
- Provide multi-modal tokenizer
- Train and release the model
1 maintainer
Metadata
1 maintainer
Release files for brave-torch 4.7.9
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| brave_torch-4.7.9.tar.gz | 6.2 kB | Without provenance | Details for brave_torch-4.7.9.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| brave_torch-4.7.9-py3-none-any.whl | Python 3 | none | any | Details for brave_torch-4.7.9-py3-none-any.whl |
Total release size: 12.7 kB
Release files / brave_torch-4.7.9.tar.gz
| Download URL | brave_torch-4.7.9.tar.gz |
|---|---|
| Size | 6.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ad2f4b63ef35520a08e8968016cc6b8870c3173b2008ba8a2655760ea0b310e6
|
|
BLAKE2b-256 checksum How to use checksums |
bb128b9ebe67ad9f7c4d74e31638e2fcbd5eb65f95c35c77a41bf3c42208dcb1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.3.2 CPython/3.11.0 Darwin/23.3.0
|
Release files / brave_torch-4.7.9-py3-none-any.whl
| Download URL | brave_torch-4.7.9-py3-none-any.whl |
|---|---|
| Size | 6.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1ecd965fe9ef4ae554a31075cde450dc3f342bc29b44f0d4d4b591f388db7c83
|
|
BLAKE2b-256 checksum How to use checksums |
eb7fe260d2829f894d9a9ab35c77dd76606566f9fc836a329393d3d0e3c3cba4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.3.2 CPython/3.11.0 Darwin/23.3.0
|
Security for brave-torch 4.7.9
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
