CoCa-pytorch
performer-pytorch
CoCa-pytorch | performer-pytorch | |
---|---|---|
1 | 2 | |
975 | 1,055 | |
- | - | |
6.2 | 1.8 | |
5 months ago | about 2 years ago | |
Python | Python | |
MIT License | MIT License |
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.
CoCa-pytorch
performer-pytorch
-
[R] Rotary Positional Embeddings - a new relative positional embedding for Transformers that significantly improves convergence (20-30%) and works for both regular and efficient attention
Performer is the best linear attention variant, but linear attention is just one type of efficient attention solution. I have rotary embeddings already in the repo https://github.com/lucidrains/performer-pytorch and you can witness this phenomenon yourself by toggling it on / off
-
Why has Google's Performer model not replaced traditional softmax attention?
Here's an PyTorch implementation if you want to play around with it: lucidrains/performer-pytorch: An implementation of Performer, a linear attention-based transformer, in Pytorch (github.com)
What are some alternatives?
DALLE-pytorch - Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
long-range-arena - Long Range Arena for Benchmarking Efficient Transformers
RETRO-pytorch - Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
Perceiver - Implementation of Perceiver, General Perception with Iterative Attention in TensorFlow
TimeSformer-pytorch - Implementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification
memory-efficient-attention-pytorch - Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"
PaLM-pytorch - Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways
reformer-pytorch - Reformer, the efficient Transformer, in Pytorch
x-clip - A concise but complete implementation of CLIP with various experimental improvements from recent papers
vit-pytorch - Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
InternVideo - Video Foundation Models & Data for Multimodal Understanding
deep-implicit-attention - Implementation of deep implicit attention in PyTorch