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-0.1.0.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-0.1.0-py3-none-any.whl (6.8 kB view details)

Uploaded Python 3

File details

Details for the file ultra_mem-0.1.0.tar.gz.

File metadata

  • Download URL: ultra_mem-0.1.0.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-0.1.0.tar.gz
Algorithm Hash digest
SHA256 7e086e0c8384b778afa7715ad8b8b98de638125b51757243e967f5ddf9337c1e
MD5 2c3bb5952f0a2ff47bcb2416203206e2
BLAKE2b-256 688d91fa32e6f8c487c1a5f3cc031f6ed778317bdce3a9eb556e49c5a2563f17

See more details on using hashes here.

File details

Details for the file ultra_mem-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: ultra_mem-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 6.8 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-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 098d3de2c8747219026fcbe4431dc6e32da4b67ccf026cebdad89fd9ab14c1ef
MD5 3a943e97b672fce6a3b3fecbd4f3d6b2
BLAKE2b-256 ac332a30d4baab5231495c32f3cb3504bf7e28cc684bf9d0a895e3a28fa2aae8

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