| --- |
| 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/<slug>/` 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. |
|
|
