CarperAI/trlx
Auf GitHub ansehenCollapse reference+learner hydra heads when using LoRa
Open
#320 geöffnet am 21. Feb. 2023
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