Spaces:
Sleeping
Sleeping
Commit History
-
fix: use train split for monology/pile-uncopyrighted (no test split exists)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>41816e0 -
fix: switch Pile corpus source to monology/pile-uncopyrighted (parquet)
EleutherAI/pile uses a dataset script which datasets >= 2.20 no longer supports. monology/pile-uncopyrighted is the same corpus hosted as parquet files with identical {"text": ...} schema. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>9f2b93b
-
fix: replace hardcoded local paths with portable defaults in eval scripts
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>da43dab -
chore: align download paths to /Flux/Projects/transformer-analysis/downloads
prepare_eval_corpus.py now writes corpus cache there by default. compute_perplexity.py --cache defaults to the same location. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>17a7cd2 -
feat: add pre-materialized Pile corpus cache for repeated eval runs
prepare_eval_corpus.py downloads a fixed gzipped JSONL sample from The Pile test split (default 500 MB, configurable). compute_perplexity.py loads from this cache via --pile-cache, avoiding streaming overhead on repeated runs. Falls back to live streaming with a warning when no cache is provided. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>b7a7e36