AranKomat / Alpha-Transformer
Alpha Zero equipped with Transformer with various novel techniques for speedup in tree search
☆23Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for Alpha-Transformer
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆47Updated 2 years ago
- Flax (JAX) implementation of Progressive Growing of GANs for Improved Quality, Stability, and Variation☆12Updated 3 years ago
- ☆29Updated 2 years ago
- Implementation of Hierarchical Transformer Memory (HTM) for Pytorch☆72Updated 3 years ago
- Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch☆23Updated 3 years ago
- ☆21Updated last year
- AdaCat☆49Updated 2 years ago
- A JAX nn library☆21Updated 8 months ago
- A python library for highly configurable transformers - easing model architecture search and experimentation.☆49Updated 2 years ago
- A GPT, made only of MLPs, in Jax☆55Updated 3 years ago
- Meta-learning inductive biases in the form of useful conserved quantities.☆37Updated last year
- A framework for implementing equivariant DL☆10Updated 3 years ago
- A simple implementation of a deep linear Pytorch module☆18Updated 4 years ago
- Official code for the paper "Context-Aware Language Modeling for Goal-Oriented Dialogue Systems"☆34Updated last year
- Official repository for the paper "Going Beyond Linear Transformers with Recurrent Fast Weight Programmers" (NeurIPS 2021)☆47Updated last year
- ☆24Updated 6 months ago
- Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper☆78Updated 3 years ago
- My explorations into editing the knowledge and memories of an attention network☆34Updated last year
- ☆27Updated 3 years ago
- An implementation of Transformer with Expire-Span, a circuit for learning which memories to retain☆33Updated 4 years ago
- A simple Transformer where the softmax has been replaced with normalization☆18Updated 4 years ago
- Generalised UDRL☆37Updated 2 years ago
- An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols☆14Updated 3 years ago
- Describe the format of image/text datasets☆11Updated 2 years ago