apunkt/doc-to-lora
1
0
Fork 0
mirror of https://github.com/SakanaAI/doc-to-lora.git synced 2026-07-26 17:11:02 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

add ctx_prefix to ctx_numbers + max_val_samples limit to 5k be default

Browse source
This commit is contained in:
51616 2025-01-04 17:48:53 +00:00
parent 64e3c723cd
commit b9c9dc3615
4 changed files with 15 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

3
data/raw_datasets/generate_data.py
View file

@ -41,6 +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."
# Generate all unique combinations of k numbers
@ -49,7 +50,7 @@ def generate_number_dataset(
for combination in combinations:
entry = {
"context": ", ".join(map(str, combination)),
"context": ctx_prefix.format(k=k) + ", ".join(map(str, combination)),
"prompt": query,
"response": ", ".join(map(str, combination)),
}