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

ctx_encoder_args + loadable modulated model + ctx_numbers_256

Browse source
This commit is contained in:
51616 2025-01-05 10:35:43 +00:00
parent 831e057eca
commit c0cf32c8af
5 changed files with 690 additions and 201 deletions
Download patch file Download diff file Expand all files Collapse all files

12
data/raw_datasets/generate_data.py
View file

@ -78,19 +78,19 @@ if __name__ == "__main__":
random.seed(42)
# Generate dataset
for k in range(2, 129):
for k in range(2, 257):
save_dir = f"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)
# 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}")
# print(f"Dataset generated and saved at {save_dir}")
for k in [512, 1024, 2048]:
save_dir = f"context_numbers_{k}"