facebookresearch/memory
View on GitHubMemory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, sparsely activated memory layers complement compute-heavy dense feed-forward layers, providing dedicated capacity to store and retrieve information cheaply.
- Stars
- 379
- Forks
- 32
- Open beginner issues
- 0
- Indexed issues
- 2
- Dominant language
- Python
- License
- No license data
- Last GitHub push
- Dec 12, 2024
- Latest indexed
- Sep 15, 2026
- Contributing guide
- Contributing guide
- Code of conduct
- Code of conduct
- Beginner labels
- No beginner labels indexed
- PR merge metrics
- No merged PRs in 30d
-
facebookresearch/memory#3 · 0 comments · 0 reactions · 0 assignees ·
-
facebookresearch/memory#4 · 1 comment · 0 reactions · 0 assignees ·