otter

LB
Li Bo
Update README.md
2 года назад
1e7eb9a

Описание

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

machine-learning

visual-language-learning

foundation-models

multi-modality

apple-vision-pro

artificial-inteligence

Языки

Python96,9%
Shell2,1%
Jupyter Notebook1%

[Code Refactor] Large Updates Since Aug (#293)

2 года назад

docs

Update credits.md

2 года назад

mimic-it

[Code Refactor] Large Updates Since Aug (#293)

2 года назад

pipeline

Update mimicit_dataset.py

2 года назад

shared_scripts

Update Demo_Data.yaml

2 года назад

src

Update modeling_persimmon.py

2 года назад

unit_tests

[Code Refactor] Large Updates Since Aug (#293)

2 года назад

xformers_model

[Code Refactor] Large Updates Since Aug (#293)

2 года назад

.gitattributes

[Code Refactor] Large Updates Since Aug (#293)

2 года назад

.gitignore

[Code Refactor] Large Updates Since Aug (#293)

2 года назад

CODE_OF_CONDUCT.md

[Code Refactor] Large Updates Since Aug (#293)

2 года назад

LICENSE

[Code Refactor] Large Updates Since Aug (#293)

2 года назад

README.md

Update README.md

2 года назад

conftest.py

[Code Refactor] Large Updates Since Aug (#293)

2 года назад

environment.yml

[Code Refactor] Large Updates Since Aug (#293)

2 года назад

pyproject.toml

[Code Refactor] Large Updates Since Aug (#293)

2 года назад

pytest.ini

[Code Refactor] Large Updates Since Aug (#293)

2 года назад

requirements.txt

Update requirements.txt

2 года назад

setup.py

Pufanyi/clip vision model (#317)

2 года назад

Readme

README.md

Описание

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

visual-language-learning

foundation-models

multi-modality

apple-vision-pro

artificial-inteligence

egocentric-vision

embodied