apunkt/doc-to-lora
1
0
Fork 0
mirror of https://github.com/SakanaAI/doc-to-lora.git synced 2026-07-23 17:01:04 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

install + data folder for fav num

Browse source
This commit is contained in:
51616 2025-06-19 04:21:52 +09:00
parent bacbe7673e
commit 4a5773bf69
2 changed files with 31 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

33
data/generate_fav.py
View file

@ -74,24 +74,31 @@ if __name__ == "__main__":
# Set random seed for reproducibility
random.seed(42)
# Generate dataset
for k in range(2, 257):
save_dir = f"context_numbers_{k}"
for k in range(2, 11):
save_dir = f"data/raw_datasets/context_numbers_{k}"
os.makedirs(save_dir, exist_ok=True)
generate_number_dataset(n=12_000, k=k, save_dir=save_dir)
print(f"Dataset generated and saved at {save_dir}")
# for k in range(144, 257, 16):
# save_dir = f"context_numbers_{k}"
# # Generate dataset
# for k in range(2, 257):
# save_dir = f"data/raw_datasets/context_numbers_{k}"
# os.makedirs(save_dir, exist_ok=True)
# generate_number_dataset(n=12_000, k=k, save_dir=save_dir)
# print(f"Dataset generated and saved at {save_dir}")
# # for k in range(144, 257, 16):
# # save_dir = f"context_numbers_{k}"
# # os.makedirs(save_dir, exist_ok=True)
# # generate_number_dataset(n=100_000, k=k, save_dir=save_dir)
# # print(f"Dataset generated and saved at {save_dir}")
# for k in [512]:
# save_dir = f"data/raw_datasets/context_numbers_{k}"
# os.makedirs(save_dir, exist_ok=True)
# generate_number_dataset(n=100_000, k=k, save_dir=save_dir)
# print(f"Dataset generated and saved at {save_dir}")
for k in [512]:
save_dir = f"context_numbers_{k}"
os.makedirs(save_dir, exist_ok=True)
generate_number_dataset(n=100_000, k=k, save_dir=save_dir)
print(f"Dataset generated and saved at {save_dir}")
# print(f"Dataset generated and saved at {save_dir}")

13
install.sh
View file

@ -7,14 +7,23 @@
# # cd lm-evaluation-harness
# # git checkout f724be699e8adf7ca8004ea0e519dfac83a06f18
# # pip install -e .
module load cuda/12.4
module load cudnn/9.1.0
module load hpcx/v2.21
uv self update
uv venv --python 3.10 --seed
# uv pip install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 --index-url https://download.pytorch.org/whl/cu124
# uv pip install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 --torch-backend=auto
uv run python -m pip install torch==2.6.0 torchvision==0.21.0 torchaudio==2.6.0 --torch-backend=auto
uv pip install torch==2.6.0 torchvision==0.21.0 torchaudio==2.6.0 --torch-backend=cu124
# uv pip install torch==2.7.1 torchvision==0.22.1 torchaudio==2.7.1 --torch-backend=cu128
uv sync
uv run python -m pip install https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
uv pip install https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
# uv pip install flash-attn==2.6.3 --no-build-isolation
# needed for gated models
uv run huggingface-cli login
# dev
uv run pre-commit install