Rishit-dagli / Compositional-Attention
An implementation of Compositional Attention: Disentangling Search and Retrieval by MILA
☆14Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for Compositional-Attention
- Implementation of a holodeck, written in Pytorch☆17Updated last year
- Describe the format of image/text datasets☆11Updated 2 years ago
- Directed masked autoencoders☆14Updated last year
- PyTorch Implementation of the paper "MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training"☆23Updated last week
- Load any clip model with a standardized interface☆21Updated 6 months ago
- Minimum Description Length probing for neural network representations☆16Updated last week
- ☆16Updated 2 years ago
- ☆15Updated 3 years ago
- ☆6Updated 11 months ago
- Official repository for the paper "Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules" (ICLR 2023)☆12Updated last year
- An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols☆14Updated 3 years ago
- code for paper "Accessing higher dimensions for unsupervised word translation"☆21Updated last year
- Shows how to do parameter ensembling using differential evolution.☆10Updated 2 years ago
- A library for simplifying fine tuning with multi gpu setups in the Huggingface ecosystem.☆15Updated 3 weeks ago
- Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification☆11Updated last year
- Implementation of Metaformer, but in an autoregressive manner☆23Updated 2 years ago
- GPT-jax based on the official huggingface library☆13Updated 3 years ago
- Simple script to re-rank images using OpenAI's CLIP https://github.com/openai/CLIP.☆16Updated 3 years ago
- Local Attention - Flax module for Jax☆20Updated 3 years ago
- Implementation of N-Grammer in Flax☆16Updated 2 years ago
- DiCE: The Infinitely Differentiable Monte-Carlo Estimator☆30Updated last year