DAMO-NLP-SG / Inf-CLIP

The official CLIP training codebase of Inf-CL: "Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss". A super memory-efficiency CLIP training scheme.

Date Created 2024-10-16 (2 months ago)

Commits 29 (last one 2 months ago)

Stargazers 216 (0 this week)

Watchers 6 (0 this week)

Forks 9

License apache-2.0

Ranking

RepositoryStats indexes 598,732 repositories, of these DAMO-NLP-SG/Inf-CLIP is ranked #171,897 (71st percentile) for total stargazers, and #301,445 for total watchers. Github reports the primary language for this repository as Python, for repositories using this language it is ranked #30,579/120,199.

Other Information

DAMO-NLP-SG/Inf-CLIP has Github issues enabled, there are 2 open issues and 1 closed issue.

All Topics

clip ring-attention flash-attention memory-efficient infinite-batch-size contrastive-learning

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

29 commits on the default branch (main) since jan '22

Yearly Commits

Commits to the default branch (main) per year

Issue History

Languages

The primary language is Python but there's also others...

updated: 2024-12-26 @ 04:15am, id: 873582274 / R_kgDONBHOwg