self-gen data viewer

This commit is contained in:
51616 2025-10-10 08:09:46 +00:00
parent fc086356b4
commit cddb1238ff
5 changed files with 638 additions and 2 deletions

View file

@ -16,5 +16,5 @@ done
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
uv run data/self_generate_qa.py --vllm_model google/gemma-2-2b-it --ds_names squad_compact ropes_compact drop_compact --split train --closed_qa_prob 1.0
uv run data/self_generate_qa.py --vllm_model google/gemma-2-2b-it --ds_names pwc_compact --split train --closed_qa_prob 0.0