mirror of
https://github.com/SakanaAI/doc-to-lora.git
synced 2026-07-23 17:01:04 +02:00
iclr cleanup
This commit is contained in:
parent
8745db6e11
commit
b6679ba755
171 changed files with 219 additions and 248151 deletions
20
scripts/main_exp/gen_data.sh
Normal file
20
scripts/main_exp/gen_data.sh
Normal file
|
|
@ -0,0 +1,20 @@
|
|||
# download fineweb_edu to `data/raw_datasets/fineweb_edu
|
||||
uv run data/download_fineweb_edu.py
|
||||
|
||||
# generate qa data
|
||||
# run from 000 to 013
|
||||
for shard_id in $(seq -f "%03g" 0 1); do
|
||||
uv run data/generate_fw_edu_qa_v2.py --shard_pattern "${shard_id}_00000" --n_qa_pairs=5 --vllm_model=google/gemma-3-12b-it --max_length=2000 --max_model_length=2048;
|
||||
uv run data/generate_fw_edu_qa_v2_repeat.py --shard_pattern "min_0_to_2000/${shard_id}*level_0*" --n_qa_pairs=5 --vllm_model=google/gemma-3-12b-it;
|
||||
|
||||
# self-generated response QA data
|
||||
uv run data/self_generate_qa.py --vllm_model google/gemma-2-2b-it --glob_pattern "data/raw_datasets/fw_qa_v2/min_0_to_2000/${shard_id}*_level_1*" --closed_qa_prob 1.0
|
||||
done
|
||||
|
||||
|
||||
# val split
|
||||
uv run data/self_generate_qa.py --vllm_model google/gemma-2-2b-it --glob_pattern 'data/raw_datasets/fw_qa_v2/min_0_to_2000/*_level_0_val.parquet'
|
||||
|
||||
# self-gen data for other ds
|
||||
uv run data/self_generate_qa.py --vllm_model google/gemma-2-2b-it --ds_names squad_compact ropes_compact drop_compact --closed_qa_prob 1.0
|
||||
uv run data/self_generate_qa.py --vllm_model google/gemma-2-2b-it --ds_names pwc_compact --closed_qa_prob 0.0
|
||||
Loading…
Add table
Add a link
Reference in a new issue