| .. |
|
eval/triviaqa
|
add len info eval + triviaqa_retrieved
|
2025-05-26 09:16:35 +00:00 |
|
build_drop_compact.py
|
tiny configs + fix dataset gen (remove repeated response + qa template for compact ds) + add ropes and drop eval ds
|
2025-06-30 16:10:52 +09:00 |
|
build_pwc_compact.py
|
tiny configs + fix dataset gen (remove repeated response + qa template for compact ds) + add ropes and drop eval ds
|
2025-06-30 16:10:52 +09:00 |
|
build_ropes_compact.py
|
tiny configs + fix dataset gen (remove repeated response + qa template for compact ds) + add ropes and drop eval ds
|
2025-06-30 16:10:52 +09:00 |
|
build_squad_compact.py
|
tiny configs + fix dataset gen (remove repeated response + qa template for compact ds) + add ropes and drop eval ds
|
2025-06-30 16:10:52 +09:00 |
|
create_test_data.py
|
Store top k logits tests and scripts (#2) (to be refactored + integrated with data pipeline)
|
2025-07-09 13:18:15 +09:00 |
|
download_fineweb_edu.py
|
data scripts + readme
|
2025-06-06 09:48:42 +00:00 |
|
download_generated_fineweb_qa.py
|
download generated fw qa
|
2025-06-26 16:24:18 +09:00 |
|
download_self_gen_qa.py
|
download self gen qa
|
2025-06-26 16:30:04 +00:00 |
|
generate_fav.py
|
install + data folder for fav num
|
2025-06-19 04:21:52 +09:00 |
|
generate_fav_num_big.py
|
data gen scripts
|
2025-05-30 03:11:03 +00:00 |
|
generate_fw_edu_augment_vllm.py
|
data scripts + readme
|
2025-06-06 09:48:42 +00:00 |
|
generate_fw_edu_qa_v2.py
|
small adjustment data gen (remove empty)
|
2025-07-03 11:02:46 +00:00 |
|
generate_fw_edu_qa_v2_repeat.py
|
small adjustment data gen (remove empty)
|
2025-07-03 11:02:46 +00:00 |
|
generate_fw_edu_qa_vllm.py
|
data gen scripts
|
2025-05-30 03:11:03 +00:00 |
|
generate_negative_natural_questions.py
|
data gen scripts
|
2025-05-30 03:11:03 +00:00 |
|
generate_pretrain_from_fw_qa.py
|
data scripts + readme
|
2025-06-06 09:48:42 +00:00 |
|
self_generate_qa.py
|
self-gen w/ closed_qa format + perceiver scripts + no strip response
|
2025-07-08 14:21:43 +00:00 |
|
store_top_logits.py
|
Store top k logits tests and scripts (#2) (to be refactored + integrated with data pipeline)
|
2025-07-09 13:18:15 +09:00 |