Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add LVMs LLaVA component #181

Merged
merged 26 commits into from
Jun 19, 2024
Merged

Add LVMs LLaVA component #181

merged 26 commits into from
Jun 19, 2024

Conversation

Spycsh
Copy link
Member

@Spycsh Spycsh commented Jun 14, 2024

Description

Add LVMs LLaVA component

Issues

n/a

Type of change

List the type of change like below. Please delete options that are not relevant.

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds new functionality)
  • Breaking change (fix or feature that would break existing design and interface)

Dependencies

None

Tests

tests/test_lvm.sh

Copy link

codecov bot commented Jun 14, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Files Coverage Δ
comps/cores/mega/constants.py 98.00% <100.00%> (ø)
comps/cores/proto/docarray.py 100.00% <100.00%> (ø)

Copy link
Collaborator

@hshen14 hshen14 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Shall we call "Img2txt" to "LVM"? Image to text sounds too specific.

LVM means large visual model.

@Spycsh
Copy link
Member Author

Spycsh commented Jun 17, 2024

Shall we call "Img2txt" to "LVM"? Image to text sounds too specific.

LVM means large visual model.

Hi @hshen14 The original design here is to not only use LLaVA as the base model which convert image+prompt => text, but also adaptable to use image-captioning models such as vit, blip, which simply convert image=>text. So here I think img2txt is a more general term. What do you think?

@Spycsh Spycsh changed the title Add Img2txt LLaVA component Add LVMs (Large Visual Models) component Jun 17, 2024
@Spycsh Spycsh changed the title Add LVMs (Large Visual Models) component Add LVMs LLaVA component Jun 17, 2024
@Spycsh Spycsh merged commit bd385be into opea-project:main Jun 19, 2024
9 checks passed
sharanshirodkar7 pushed a commit to sharanshirodkar7/GenAIComps that referenced this pull request Jul 9, 2024
* add img2txt microservice

Signed-off-by: Spycsh <sihan.chen@intel.com>

* fix

* rem

* fix

* fix

* debug

* add debug

* add standalone llava server to avoid tokenization in diff process issue

* add another test

* endpoint

* debug

* rem

* fix

* disable hpu graph

* dockernize

* add test

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* rem nohup

* fix

* refactor img2txt to lvms

* Update test_reranks_langchain.sh

* fix test name

* rename

* lower wait time

---------

Signed-off-by: Spycsh <sihan.chen@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>
Signed-off-by: sharanshirodkar7 <ssharanshirodkar7@gmail.com>
yogeshmpandey pushed a commit to yogeshmpandey/GenAIComps that referenced this pull request Jul 10, 2024
* add img2txt microservice

Signed-off-by: Spycsh <sihan.chen@intel.com>

* fix

* rem

* fix

* fix

* debug

* add debug

* add standalone llava server to avoid tokenization in diff process issue

* add another test

* endpoint

* debug

* rem

* fix

* disable hpu graph

* dockernize

* add test

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* rem nohup

* fix

* refactor img2txt to lvms

* Update test_reranks_langchain.sh

* fix test name

* rename

* lower wait time

---------

Signed-off-by: Spycsh <sihan.chen@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>
Signed-off-by: Yogesh Pandey <yogesh.pandey@intel.com>
dwhitena pushed a commit to predictionguard/GenAIComps that referenced this pull request Jul 24, 2024
* add img2txt microservice

Signed-off-by: Spycsh <sihan.chen@intel.com>

* fix

* rem

* fix

* fix

* debug

* add debug

* add standalone llava server to avoid tokenization in diff process issue

* add another test

* endpoint

* debug

* rem

* fix

* disable hpu graph

* dockernize

* add test

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* rem nohup

* fix

* refactor img2txt to lvms

* Update test_reranks_langchain.sh

* fix test name

* rename

* lower wait time

---------

Signed-off-by: Spycsh <sihan.chen@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>
Signed-off-by: Daniel Whitenack <whitenack.daniel@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants