kyegomez / Sophia
Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.
☆377Updated 5 months ago
Related projects ⓘ
Alternatives and complementary repositories for Sophia
- The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”☆937Updated 9 months ago
- Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch☆393Updated 8 months ago
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆224Updated 2 months ago
- Language Modeling with the H3 State Space Model☆513Updated last year
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆291Updated 4 months ago
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆205Updated 2 months ago
- A repository for log-time feedforward networks☆216Updated 7 months ago
- For optimization algorithm research and development.☆408Updated this week
- Annotated version of the Mamba paper☆455Updated 8 months ago
- Code release for "Dropout Reduces Underfitting"☆312Updated last year
- ☆292Updated 4 months ago
- Helpful tools and examples for working with flex-attention☆460Updated 2 weeks ago
- Implementation of Block Recurrent Transformer - Pytorch☆214Updated 2 months ago
- Code for the ALiBi method for transformer language models (ICLR 2022)☆506Updated last year
- Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"☆536Updated 5 months ago
- Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate …☆625Updated last year
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆359Updated last year
- Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch☆624Updated last month
- Sequence modeling with Mega.☆297Updated last year
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆968Updated 2 months ago
- Recurrent Memory Transformer☆150Updated last year
- Convolutions for Sequence Modeling☆867Updated 4 months ago
- Implementation of the Adan (ADAptive Nesterov momentum algorithm) Optimizer in Pytorch☆247Updated 2 years ago
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆474Updated 2 weeks ago
- Automatic gradient descent☆207Updated last year
- ☆161Updated last year
- Code repository for the paper - "Matryoshka Representation Learning"☆423Updated 8 months ago
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch☆565Updated last month
- FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores☆277Updated last month