Skip to main content

UltraMem

Project description

UltraMem

Implementation of UltraMem, improved Product Key Memory design, from Bytedance AI labs

Install

$ pip install ultra-mem

Usage

import torch
from ultra_mem import UltraMem

ultra_mem = UltraMem(dim = 512)

tokens = torch.randn(1, 1024, 512)

out, aux_loss = ultra_mem(tokens) # (1, 1024, 512), ()

Char-level LM

$ uv run train.py

Citations

@misc{huang2025ultrasparsememorynetwork,
    title   = {Ultra-Sparse Memory Network}, 
    author  = {Zihao Huang and Qiyang Min and Hongzhi Huang and Defa Zhu and Yutao Zeng and Ran Guo and Xun Zhou},
    year    = {2025},
    eprint  = {2411.12364},
    archivePrefix = {arXiv},
    primaryClass = {cs.LG},
    url     = {https://arxiv.org/abs/2411.12364}, 
}
@inproceedings{anonymous2025continual,
    title   = {Continual Learning via Sparse Memory Finetuning},
    author  = {Anonymous},
    booktitle = {Submitted to The Fourteenth International Conference on Learning Representations},
    year    = {2025},
    url     = {https://openreview.net/forum?id=LGo7U1m24L},
    note    = {under review}
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ultra_mem-0.0.8.tar.gz (36.8 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ultra_mem-0.0.8-py3-none-any.whl (6.7 kB view details)

Uploaded Python 3

File details

Details for the file ultra_mem-0.0.8.tar.gz.

File metadata

  • Download URL: ultra_mem-0.0.8.tar.gz
  • Upload date:
  • Size: 36.8 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.25

File hashes

Hashes for ultra_mem-0.0.8.tar.gz
Algorithm Hash digest
SHA256 53bf4b098c3396870812d1ba2eb2cf000806e469e4a3249bc74506e281336f29
MD5 64b4ca9a33229bb349f290b3e81f3fac
BLAKE2b-256 cc58da45923de160c4869be6b7158e621c25e5443da06595dd5cebd04ebd5143

See more details on using hashes here.

File details

Details for the file ultra_mem-0.0.8-py3-none-any.whl.

File metadata

  • Download URL: ultra_mem-0.0.8-py3-none-any.whl
  • Upload date:
  • Size: 6.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.25

File hashes

Hashes for ultra_mem-0.0.8-py3-none-any.whl
Algorithm Hash digest
SHA256 dca365eded18e51c75c8aa10366c6c5065cba057d1df0df210efbfa77290429a
MD5 ae15d3f8f60d84851c7206fd04aa6829
BLAKE2b-256 c28a0a7ad6ca1acb78c5d3a1b89e44521ef9d04fc8042fae7e7dccb52d5321ae

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page