AlphaUncommon
facebookresearch/memory
Memory 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.
- Owner
- facebookresearch (organization)
- Stars
- Stars: 386
- Forks
- Forks: 33
- Language
- Python
- License
- None
- Created
- 2024
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by facebookresearch
All 640 repos by facebookresearch- facebookresearch/segment-anythingStars: 55,089Jupyter NotebookLTS
- facebookresearch/faissStars: 41,246C++LTS
- facebookresearch/detectron2Stars: 34,961PythonLTS
- facebookresearch/fairseqStars: 32,211PythonLTS
- facebookresearch/fastTextStars: 26,513HTMLLTS
- facebookresearch/DetectronStars: 26,344PythonLTS
Nearby in Python
All Python repos- facok/comfyui-SelfLiftStars: 386PythonAlpha
- DefiLeoo/YOINKStars: 386PythonAlpha
- EricJujianZou/rederiveStars: 386PythonAlpha
- rupa/epubStars: 386PythonAlpha
- toffer/iphone-sms-backupStars: 386PythonAlpha
- nvie/timesStars: 386PythonAlpha