Bangkit-C22CB-Company-Based-Capstone

This is our repository for Company Based Capstone.

Our team Consist of 9 people.

• Bangkit-C22CB-Company-Based-Capstone
  • The Boys
  • What is this? (coming soon)
  • Editing Architecture Chart
  • Running Our Project in Local
    • Using Conda (easier to build)
    • Using PIP (not recommended, still experimental)
  • Our ML model result uploaded to Huggingface.co
  • References

The Boys

Name	Bangkit ID	Learning Path	Github Profile
Ananda Daffa Abdillah	M2008G0791	Machine Learning	Profile
Daffa Haj Tsaqif	M2008G0792	Machine Learning	Profile
Mario Hagi	M2191F1819	Machine Learning	Profile
Alheta Wahyu Matalarens	A2110F1435	Mobile Development	Profile
Ary Bayu Nurwicaksono	A2183F1767	Mobile Development
Hafit Abekrori	A7183F1768	Mobile Development	Profile
Muhammad Acla Alamsyah Nurdin Hamzah	C2307F2632	Cloud Computing	Profile
Aimar Anand	C2323J2836	Cloud Computing	Profile
Ariel Peaceo Gunawan	C7005F0459	Cloud Computing	Profile

What is this? (coming soon)

TBA

Editing Architecture Chart

Use Draw.IO to create our architecture chart, use this VScode Extension to edit our diagram inside the editor: Draw.io Integration in VSCode

Running Our Project in Local

Using Conda (easier to build)

if you are using conda, you can install our project using the following command:

conda create --name bangkit_capstone python=3.9
conda activate bangkit_capstone
pip install ipykernel

or this command if you are want to specify the path of the environment

conda create --prefix ./venv/ python=3.9
conda activate ./venv/
pip install ipykernel

Using PIP (not recommended, still experimental)

It's advised for machine learning aspect to use virtual environment to working with this project, this is to prevent incompatibilities with other contributors.

If you are still activate Conda, you can deactivate it by typing conda deactivate.

in the repo's directory, run the following commands one by one:

python3 -m pip install --upgrade pip
python3 -m venv venv
source venv/bin/activate | source venv/Scripts/activate
pip install -r requirements.txt

Our ML model result uploaded to Huggingface.co

Here's our working model result uploaded to Huggingface.co bert-uncased-finetuned-squad-indonesian

References

• TensorFlow and Transformers (Medium)
• AjulorC's question answering bot
• Smaller, faster, cheaper, lighter: Introducing DistilBERT, a distilled version of BERT