CarperAI/trlx

Collapse reference+learner hydra heads when using LoRa

Open

#320 geöffnet am 21. Feb. 2023

Auf GitHub ansehen
 (6 Kommentare) (2 Reaktionen) (0 zugewiesene Personen)Python (450 Forks)batch import
contributions welcomefeature requestgood first issue

Repository-Metriken

Stars
 (4.184 Stars)
PR-Merge-Metriken
 (Keine gemergten PRs in 30 T)

Beschreibung

🚀 The feature, motivation, and pitch

With additive (delta-style) parameter-efficient tuning methods such as LoRa, we should be able to make a slightly more mem-efficient hydra architecture by using a single block that does ~frozen_head + tunable_weights for the learner/policy head's fwd-pass and simply frozen_head for the reference, instead of maintaining 2x heads.

CC @LouisCastricato and @cat-state for pointing this out

Alternatives

No response

Additional context

No response

Contributor Guide