GongBU
Paper accepted by CIKM 2024. Codes of GongBU, a LLM fine-tuning platform for domain-specific adaptation.
File Explorer
Download Latest Version (.zip)- app.py
- deployment_manager.py
- openai_router.py
- eval_manager.py
- eval_script.py
- __init__.py
- adapter.py
- cuda.py
- dataset.py
- dataset_entry.py
- dataset_filter.py
- deployment.py
- eval.py
- fault.py
- file.py
- finetune.py
- finetune_entry.py
- finetune_progress.py
- ft_eval_index.py
- logging.py
- openllm.py
- pool.py
- user.py
- visibility.py
- __init__.py
- dataset.py
- fault.py
- sift.py
- deepspeed_1.json
- deepspeed_2.json
- deepspeed_2_off.json
- deepspeed_3.json
- deepspeed_3_off.json
- callback.py
- finetune_script.py
- fintune_manager.py
- generate_prompt.py
- get_deepspeed_config.py
- metrics.py
- __init__.py
- auth.py
- const.py
- db.py
- enumerate.py
- evaluate.py
- llmw.py
- main.py
- models.py
- reduce_size.py
- shared_params.py
- sync.py
- .dockerignore
- dep.md
- Dockerfile
- Dockerfile.mirror
- Dockerfile.prod
- Dockerfile.prod.mirror
- logo.webp
- logo_new.jpg
- pyproject.toml
- README.md
- requirements.txt
- GONGBU_ps.sql
- Adapter.ts
- CudaDeviceEntry.ts
- DatasetEntry.ts
- Deployment.ts
- DeploymentRequestParams.ts
- EvalEntry.ts
- EvalIndex.ts
- EvalRecord.ts
- FinetuneEntry.ts
- FinetuneEntryReduced.ts
- FinetuneProgessEntry.ts
- FinetuneRequestParams.ts
- LoggingRecord.ts
- OpenllmEntry.ts
- PoolEntry.ts
- en.ts
- index.ts
- zh-CN.ts
- BoolParam.svelte
- DeploymentParam.svelte
- FinetuneParam.svelte
- MultiSelection.svelte
- NumberBoxParam.svelte
- ParamGroup.svelte
- Params.ts
- RadioParam.svelte
- SelectParam.svelte
- SliderParam.svelte
- ActionPageTitle.svelte
- Chart.svelte
- Data.svelte
- DeviceInfo.svelte
- DeviceSelection.svelte
- EvalSelection.svelte
- GoBack.svelte
- ModelCard.svelte
- ModelSelection.svelte
- VisbilityButton.svelte
- +page.svelte
- +page.svelte
- Information.svelte
- +page.svelte
- +page.svelte
- +page.svelte
- DatasetTable.svelte
- PoolCard.svelte
- Uploader.svelte
- +page.svelte
- WrappedIframe.svelte
- +page.svelte
- Device.svelte
- +page.svelte
- DeploymentCard.svelte
- +page.svelte
- +page.svelte
- +page.svelte
- +page.svelte
- EvalCard.svelte
- EvalProgress.svelte
- +page.svelte
- +page.svelte
- TaggedSearchbar.svelte
- +page.svelte
- Charts.svelte
- EvalIndexChart.svelte
- +page.svelte
- +page.svelte
- FinetuneCard.svelte
- FinetuneProgess.svelte
- +page.svelte
- +page.svelte
- +layout.svelte
- +page.svelte
- Header.svelte
- Login.svelte
- shared.ts
- Sidebar.svelte
- Signup.svelte
- store.ts
- ConvertDatetimeString.ts
- app.css
- app.d.ts
- app.html
- hook.ts
- favicon.png
- logo.jpg
- logo.webp
- logo_full.jpg
- logo_new.jpg
- robots.txt
- .dockerignore
- .prettierignore
- .prettierrc
- Dockerfile
- Dockerfile.mirror
- Dockerfile.prod
- Dockerfile.prod.mirror
- package.json
- postcss.config.cjs
- README.md
- svelte.config.js
- tailwind.config.cjs
- tsconfig.json
- vite.config.ts
- 502.html
- Dockerfile
- Dockerfile.prod
- nginx.conf
- nginx.prod.conf
- image.png
- .gitignore
- docker-compose.mirror.yaml
- docker-compose.prod.mirror.yaml
- docker-compose.prod.yaml
- docker-compose.yaml
- download.py
- LICENSE
- README.md
# Installation Guide
1. Get the code
git clone https://github.com/Bolin97/GongBU
Downloads the entire project code from GitHub to your computer.
cd GongBU
Moves into the project folder you just downloaded.
2. Docker
Easy RecommendedPrerequisites
- Git Needed to download the project code from GitHub.
- Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
docker compose -f docker-compose.prod.yaml up
Runs the command against the services defined in the compose file.
Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.
Pulled directly from this repo's README.
3. Node.js
EasyPrerequisites
cd frontend
This project's files live in a subfolder, so move into it first.
npm install
Downloads and installs the libraries listed in package.json.
npm start
Starts the development/run server.
After running the command, open the address shown in the terminal (usually something like http://localhost:3000) in your browser.
4. Python
EasyPrerequisites
pip install -r backend/requirements.txt
Installs the Python libraries listed in requirements.txt (or similar).
python <์คํํ ํ์ผ๋ช
>.py # README์์ ์ ํํ ์คํ ํ์ผ๋ช
์ ํ์ธํ์ธ์
Runs the Python script (or module).
If it runs without errors and prints output in the terminal, it worked.
// repository documentation
Was this content helpful?
(0 ratings)