qmd/finetune/data
Tobi Lutke 785620467a
refactor: reorder output format to put hyde line first
Move the hyde (hypothetical document) line to the beginning of the
output format, before lex and vec lines. This better reflects the
logical flow where the hypothetical document is generated first and
then informs the keyword/semantic expansions.

Also adds auto-download of eval_common.py in training scripts for
standalone HuggingFace Jobs execution.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-31 12:09:04 -05:00
..
train Refactor finetune folder: train/rl scripts with YAML configs 2026-01-24 20:26:46 -05:00
train_v2 Deploy fine-tuned GRPO model as default for query expansion 2026-01-28 23:24:58 -08:00
qmd_expansion_v2.jsonl refactor: reorder output format to put hyde line first 2026-01-31 12:09:04 -05:00