806 MB

Ctrl+K

1 contributor

Replace single canonical head with 6 decode-matched paper heads (mistral+llama x hh-rlhf/beavertails/pku_saferlhf), per-backbone layout + conformal alpha-curve sidecars

3515b78 verified 27 days ago

llama
Replace single canonical head with 6 decode-matched paper heads (mistral+llama x hh-rlhf/beavertails/pku_saferlhf), per-backbone layout + conformal alpha-curve sidecars 27 days ago
mistral
Replace single canonical head with 6 decode-matched paper heads (mistral+llama x hh-rlhf/beavertails/pku_saferlhf), per-backbone layout + conformal alpha-curve sidecars 27 days ago
.gitattributes

1.52 kB
initial commit 2 months ago
README.md

2.71 kB
Replace single canonical head with 6 decode-matched paper heads (mistral+llama x hh-rlhf/beavertails/pku_saferlhf), per-backbone layout + conformal alpha-curve sidecars 27 days ago