GradCache
Run Effective Large Batch Contrastive Learning Beyond GPU/TPU Memory Constraint (by luyug)
long-range-arena
Long Range Arena for Benchmarking Efficient Transformers (by google-research)
| GradCache | long-range-arena | |
|---|---|---|
| 1 | 6 | |
| 310 | 684 | |
| - | 1.0% | |
| 4.5 | 0.0 | |
| about 2 months ago | 5 months ago | |
| Python | Python | |
| Apache License 2.0 | Apache License 2.0 |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
GradCache
Posts with mentions or reviews of GradCache.
We have used some of these posts to build our list of alternatives
and similar projects.
-
[D] How to handle absurd batch sizes in SimCLR / OpenAI's CLIP?
Maybe you should try this thing: https://github.com/luyug/GradCache
long-range-arena
Posts with mentions or reviews of long-range-arena.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-06-17.
-
The Secret Sauce behind 100K context window in LLMs: all tricks in one place
https://github.com/google-research/long-range-arena
-
[R] The Annotated S4: Efficiently Modeling Long Sequences with Structured State Spaces
The Structured State Space for Sequence Modeling (S4) architecture is a new approach to very long-range sequence modeling tasks for vision, language, and audio, showing a capacity to capture dependencies over tens of thousands of steps. Especially impressive are the model’s results on the challenging Long Range Arena benchmark, showing an ability to reason over sequences of up to 16,000+ elements with high accuracy.
-
[D] Is there a repo on which many light-weight self-attention mechanism are introduced?
1.1 Long Range Arena: A Benchmark for Efficient Transformers. From authors of above, they proposed a benchmark for modeling long range interactions. It also inlcudes a repository
- [R] Google’s H-Transformer-1D: Fast One-Dimensional Hierarchical Attention With Linear Complexity for Long Sequence Processing
- [2107.11906] H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences
-
[R][D] Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. Zhou et al. AAAI21 Best Paper. ProbSparse self-attention reduces complexity to O(nlogn), generative style decoder to obtainsequence output in one step, and self-attention distilling for further reducing memory
I think the paper is written in a clear style and I like that the authors included many experiments, including hyperparameter effects, ablations and extensive baseline comparisons. One thing I would have liked is them comparing their Informer to more efficient transformers (they compared only against logtrans and reformer) using the LRA (https://github.com/google-research/long-range-arena) benchmark.
What are some alternatives?
When comparing GradCache and long-range-arena you can also consider the following projects:
h-former - H-Former is a VAE for generating in-between fonts (or combining fonts). Its encoder uses a Point net and transformer to compute a code vector of glyph. Its decoder is composed of multiple independent decoders which act on a code vector to reconstruct a point cloud representing a glpyh.
performer-pytorch - An implementation of Performer, a linear attention-based transformer, in Pytorch