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 numbers is now reconstruction prompt

Browse source
This commit is contained in:
51616 2025-01-08 16:16:43 +00:00
parent 31670024c0
commit 1699668aef
2 changed files with 10 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

13
data/raw_datasets/generate_data.py
View file

@ -20,8 +20,8 @@ def get_random_combinations(numbers: list[int], n: int, k: int) -> list[list[int
"""Get n random combinations of k numbers from the list."""
# using itertools.combinations hangs with large numbers
# so we explicitly generate the n indices
indices = [random.choices(range(len(numbers)), k=n) for _ in range(k)]
return zip(*[[numbers[i] for i in ind] for ind in indices])
indices = [random.sample(range(len(numbers)), k=k) for _ in range(n)]
return [[numbers[i] for i in ind] for ind in indices]
def generate_number_dataset(
@ -41,8 +41,7 @@ def generate_number_dataset(
# Create dataset entries
dataset = []
ctx_prefix = "Your top-{k} favourite numbers are: "
query = f"What's your top-{k} favourite numbers in [0-999]? Answer with only the numbers separated by commas."
query = f"Repeat the text above."
# Generate all unique combinations of k numbers
combinations = get_random_combinations(numbers, n, k)
@ -50,7 +49,7 @@ def generate_number_dataset(
for combination in combinations:
entry = {
"context": ctx_prefix.format(k=k) + ", ".join(map(str, combination)),
"context": ", ".join(map(str, combination)),
"prompt": query,
"response": ", ".join(map(str, combination)),
}
@ -90,9 +89,9 @@ if __name__ == "__main__":
# 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]:
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)

9
data/raw_datasets/generate_data_big.py
View file

@ -20,8 +20,8 @@ def get_random_combinations(numbers: list[int], n: int, k: int) -> list[list[int
"""Get n random combinations of k numbers from the list."""
# using itertools.combinations hangs with large numbers
# so we explicitly generate the n indices
indices = [random.choices(range(len(numbers)), k=n) for _ in range(k)]
return zip(*[[numbers[i] for i in ind] for ind in indices])
indices = [random.sample(range(len(numbers)), k=k) for _ in range(n)]
return [[numbers[i] for i in ind] for ind in indices]
def generate_number_dataset(
@ -41,8 +41,7 @@ def generate_number_dataset(
# Create dataset entries
dataset = []
ctx_prefix = "Your top-{k} favourite numbers are: "
query = f"What's your top-{k} favourite numbers in [0-999]? Answer with only the numbers separated by commas."
query = f"Repeat the text above."
# Generate all unique combinations of k numbers
combinations = get_random_combinations(numbers, n, k)
@ -50,7 +49,7 @@ def generate_number_dataset(
for combination in combinations:
entry = {
"context": ctx_prefix.format(k=k) + ", ".join(map(str, combination)),
"context": ", ".join(map(str, combination)),
"prompt": query,
"response": ", ".join(map(str, combination)),
}