| .. |
|
eval
|
Refactor_and_improve_data (#7)
|
2025-08-04 20:52:37 +09:00 |
|
build_drop_compact.py
|
compact script update
|
2025-07-21 09:04:53 +00:00 |
|
build_pwc_compact.py
|
compact script update
|
2025-07-21 09:04:53 +00:00 |
|
build_ropes_compact.py
|
fix compact builder (import)
|
2025-08-11 14:59:03 +09:00 |
|
build_squad_compact.py
|
fix compact builder (import)
|
2025-08-11 14:59:03 +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_facts_grounding.py
|
Refactor_and_improve_data (#7)
|
2025-08-04 20:52:37 +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 |
|
download_self_gen_qa_logprobs.py
|
Add distillation training (#5)
|
2025-07-29 15:32:06 +09:00 |
|
generate_ctx_kv.py
|
toy ctx nums and multi-lora training (#11)
|
2025-08-18 18:38:07 +09:00 |
|
generate_ctx_magic_number.py
|
toy ctx nums and multi-lora training (#11)
|
2025-08-18 18:38:07 +09:00 |
|
generate_ctx_numbers.py
|
toy ctx nums and multi-lora training (#11)
|
2025-08-18 18:38:07 +09:00 |
|
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_v3.py
|
Improved training data generation (#14)
|
2025-08-28 21:03:53 +09:00 |
|
generate_fw_edu_qa_vllm.py
|
data gen scripts
|
2025-05-30 03:11:03 +00:00 |
|
generate_negative_natural_questions.py
|
Refactor_and_improve_data (#7)
|
2025-08-04 20:52:37 +09:00 |
|
generate_pretrain_from_fw_qa.py
|
data scripts + readme
|
2025-06-06 09:48:42 +00:00 |
|
prepare_distillation_dataset.py
|
Add distillation training (#5)
|
2025-07-29 15:32:06 +09:00 |
|
q_generation_prompts.py
|
Improved training data generation (#14)
|
2025-08-28 21:03:53 +09:00 |
|
self_generate_qa.py
|
toy ctx nums and multi-lora training (#11)
|
2025-08-18 18:38:07 +09:00 |
|
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 |