--- license: llama2 library_name: pytorch tags: - reproducibility - representation-inversion - reviewer-artifact --- # Vec2Seq reviewer checkpoints for Llama-2-7b-hf This repository contains a deliberately compact reviewer subset: 7 selected Vec2Seq attacker checkpoints (12795198066 bytes). It does not contain the frozen victim model or tokenizer. Obtain `meta-llama/Llama-2-7b-hf` at immutable revision `01c7f73d771dfac7d292323805ebc428287df4f9` under its upstream terms. The subset fixes training seed 1234 to cover the three primary observation surfaces, full-sequence reconstruction at width 32, the direct-only prefix mode, and both corrected alternative poolers. Seed 1234 is a coverage choice, not an independent statistical sample. The companion code artifact contains the complete 632-row evidence registry and statistics; this repository supports the strict two-dataset audit listed in `metadata/reviewer_evaluations.csv`. Each `runs//` directory contains one checkpoint and its sanitized resolved configuration. The raw `.pt` files preserve the exact production SHA-256 values. They contain attacker-module state and runtime metadata but no victim weights, optimizer state, or EMA payload. Verify `SHA256SUMS` before loading them. Use the frozen protocol named by each manifest row. Primary and length rows use `cache_mask_v1`; alternative-pooler and direct-only rows use `cache_mask_modes_v1` with both architecture fields supplied explicitly. The validity mask, locked dataset hashes, metric definitions, and reference outputs are specified in the companion code artifact. The other selected checkpoints are formally deferred. Consequently this subset does not by itself regenerate every multi-seed interval, table, or figure.