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

tiny configs + fix dataset gen (remove repeated response + qa template for compact ds) + add ropes and drop eval ds

Browse source
This commit is contained in:
51616 2025-06-30 16:10:52 +09:00
parent e4cb1ffa55
commit 28eb85a2f3
19 changed files with 626 additions and 36 deletions
Download patch file Download diff file Expand all files Collapse all files

4
data/build_drop_compact.py
View file

@ -3,6 +3,8 @@ import gc
from datasets import Dataset, load_dataset
from tqdm import tqdm
from ctx_to_lora.data.processing import closed_qa_prompting
if __name__ == "__main__":
ds_name = "ucinlp/drop"
@ -14,7 +16,7 @@ if __name__ == "__main__":
ctx = sample["passage"]
if ctx not in ctx_qa_dict:
ctx_qa_dict[ctx] = {"prompts": [], "responses": []}
question = sample["question"]
question = closed_qa_prompting(sample["question"])
answer = ", ".join(set(sample["answers_spans"]["spans"]))
ctx_qa_dict[ctx]["prompts"].append(question)
ctx_qa_dict[ctx]["responses"].append(answer)