mirror of
https://github.com/SakanaAI/doc-to-lora.git
synced 2026-07-23 17:01:04 +02:00
* faster slice * add facts + ctx_qa * new configs * new scripts * intx_sft.py to train.py * add kaggle for downloading facts * max_new_tokens cli for eval * generate negative_nq * scripts + configs * default vals * max_val_samples_per_ds=500 * more efficient layer-to-layer ctx encoder * use_per_ctx_average_loss * faster processing * small exp distill * scripts * more robust watcher * per-module l1_norm avg * per-ctx average loss * clear_gpu |
||
|---|---|---|
| .. | ||
| eval | ||
| build_drop_compact.py | ||
| build_pwc_compact.py | ||
| build_ropes_compact.py | ||
| build_squad_compact.py | ||
| create_test_data.py | ||
| download_facts_grounding.py | ||
| download_fineweb_edu.py | ||
| download_generated_fineweb_qa.py | ||
| download_self_gen_qa.py | ||
| download_self_gen_qa_logprobs.py | ||
| generate_fav.py | ||
| generate_fav_num_big.py | ||
| generate_fw_edu_augment_vllm.py | ||
| generate_fw_edu_qa_v2.py | ||
| generate_fw_edu_qa_v2_repeat.py | ||
| generate_fw_edu_qa_vllm.py | ||
| generate_negative_natural_questions.py | ||
| generate_pretrain_from_fw_qa.py | ||
| prepare_distillation_dataset.py | ||
| self_generate_qa.py | ||
| store_top_logits.py | ||