myazdani / formal-algorithms-for-transformers
PyTorch implementation of algorithms in https://arxiv.org/abs/2207.09238
☆14Updated 2 years ago
Alternatives and similar repositories for formal-algorithms-for-transformers
Users that are interested in formal-algorithms-for-transformers are comparing it to the libraries listed below
Sorting:
- Simplifying parsing of large jsonline files in NLP Workflows☆12Updated 3 years ago
- Analogous Safe-state Exploration (ASE) is an algorithm for provably safe and optimal exploration in MDPs with unknown, stochastic dynamic…☆11Updated 4 years ago
- A framework for implementing equivariant DL☆10Updated 3 years ago
- Minimum Description Length probing for neural network representations☆19Updated 3 months ago
- Experimental version of jxbz/agd implementing support for bias terms, affine parameters, transformers, etc.☆11Updated last year
- Code for our ICLR Trustworthy ML 2020 workshop paper "Improved Image Wasserstein Attacks and Defenses"☆14Updated 5 years ago
- An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols☆15Updated 3 years ago
- Investigate the speed of adaptation of structural causal models☆15Updated 4 years ago
- Automatically generate simple meta-learning tasks from a very large space☆15Updated last year
- Easily serialize dataclasses to and from tensors (PyTorch, NumPy)☆18Updated 4 years ago
- Quasi-Newton Algorithm for Stochastic Optimization☆10Updated 2 years ago
- Multithreaded elementwise algebra and random number generation☆8Updated last year
- 📰 Computing the information content of trained neural networks☆21Updated 3 years ago
- Understanding RL vision Distill article☆23Updated 2 years ago
- Quantification of Uncertainty with Adversarial Models☆28Updated last year
- High-performance tokenized language data-loader for Python C++ extension☆13Updated 9 months ago
- Implementations of growing and pruning in neural networks☆22Updated last year
- Scalable Computation of Hessian Diagonals☆13Updated 11 months ago
- Evolution of Discrete data with Reinforcement Learning☆13Updated 5 years ago
- Neural Tangent Kernel (NTK) module for the scikit-learn library☆25Updated 7 months ago
- Code for "Counterfactual Token Generation in Large Language Models", Arxiv 2024.☆25Updated 6 months ago
- Code for Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding☆22Updated 2 years ago
- A tutorial on JAX (https://github.com/google/jax/)☆46Updated 6 years ago
- Pytorch based implementation of Upside Down Reinforcement Learning (UDRL) by J. Schmidhuber et al.☆11Updated 5 years ago
- Source-to-Source Debuggable Derivatives in Pure Python☆15Updated last year
- Applying Reinforcement Learning from Human Feedback to language models to teach them to write short story responses to writing prompts.☆14Updated 3 years ago
- The Concept Bottleneck Shift Detection (CBSD) methods for explaining and detecting various dataset shifts.☆14Updated 3 years ago
- Implements EvoNorms B0 and S0 as proposed in Evolving Normalization-Activation Layers.☆11Updated 5 years ago
- Ludwig benchmark☆20Updated 3 years ago
- ☆8Updated 10 months ago