How to install Jiayi-Pan/TinyZero. Official installation instructions. Project installation guide. Framework or library installation. Build installation instructions. How to setup and install from GitHub. Installation steps and setup instructions. Official docs and installation instructions GitHub.
Jiayi-Pan/TinyZero Installation Guide
How to install Jiayi-Pan/TinyZero. Official project installation instructions and setup guide.
⚡
Automated Install (Recommended)
Quick installation instructions for Jiayi-Pan/TinyZero. This is the fastest way to complete project installation and setup.
Install via curl
curl -fsSL https://hexmos.com/ipm-install | bash &&
ipm i Jiayi-Pan/TinyZeroor
Install via npx
npx @hexmos/ipm i Jiayi-Pan/TinyZeroPrerequisites
Python
languageVersion: 3.9.0
torch
package_managerVersion: 2.4.0
vllm
package_managerVersion: 0.6.3
ray
package_managerVersion: 1.2.0
veRL
system_toolVersion: vllm-specific-version
wandb
libraryVersion: 0.12.0
IPython
libraryVersion: 7.23.0
matplotlib
libraryVersion: 4.1.1
flash-attn
package_managerVersion: 0.5.4
conda
system_toolVersion: 4.13.0
Manual Installation Methods
Manual installation instructions. How to install from GitHub source.
Package Manager
conda create -n zero python=3.9
pip install torch==2.4.0 --index-url https://download.pytorch.org/whl/cu121
pip install vllm==0.6.3
pip3 install ray
verlScript
conda activate zero
python ./examples/data_preprocess/countdown.py --local_dir {path_to_your_dataset}
bash ./scripts/train_tiny_zero.shShell Script
export N_GPUS=1
export BASE_MODEL={path_to_your_model}
export DATA_DIR={path_to_your_dataset}
export ROLLOUT_TP_SIZE=1
export EXPERIMENT_NAME=countdown-qwen2.5-0.5b
export VLLM_ATTENTION_BACKEND=XFORMERS
bash ./scripts/train_tiny_zero.shShell Script
export N_GPUS=2
export BASE_MODEL={path_to_your_model}
export DATA_DIR={path_to_your_dataset}
export ROLLOUT_TP_SIZE=2
export EXPERIMENT_NAME=countdown-qwen2.5-3b
export VLLM_ATTENTION_BACKEND=XFORMERS
bash ./scripts/train_tiny_zero.shShell Script
export N_GPUS=2
export BASE_MODEL={path_to_your_model}
export DATA_DIR={path_to_your_dataset}
export ROLLOUT_TP_SIZE=2
export EXPERIMENT_NAME=countdown-qwen2.5-3b-instruct
export VLLM_ATTENTION_BACKEND=XFORMERS
bash ./scripts/train_tiny_zero.shPost Installation Steps
- Start the server using `python app.py`.
- Run migrations with `python manage.py makemigrations && python manage.py migrate`
