Liuhong99 / SophiaLinks
The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”
☆979Updated last year
Alternatives and similar repositories for Sophia
Users that are interested in Sophia are comparing it to the libraries listed below
Sorting:
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆384Updated last year
- Cramming the training of a (BERT-type) language model into limited compute.☆1,353Updated last year
- Convolutions for Sequence Modeling☆906Updated last year
- maximal update parametrization (µP)☆1,636Updated last year
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆1,014Updated last year
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,136Updated last year
- Language Modeling with the H3 State Space Model☆519Updated 2 years ago
- Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch☆654Updated 11 months ago
- Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"☆560Updated 11 months ago
- Annotated version of the Mamba paper☆491Updated last year
- Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch☆420Updated 11 months ago
- 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch☆2,174Updated last year
- minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.☆489Updated 2 years ago
- A repository for research on medium sized language models.☆520Updated 6 months ago
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,630Updated last year
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆548Updated 6 months ago
- ☆788Updated 2 weeks ago
- Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate …☆637Updated 2 years ago
- Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"☆1,063Updated last year
- LOMO: LOw-Memory Optimization☆991Updated last year
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways☆827Updated 3 years ago
- For optimization algorithm research and development.☆547Updated 2 weeks ago
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,293Updated 11 months ago
- Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript☆606Updated last year
- Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates☆469Updated last year
- Code for the ALiBi method for transformer language models (ICLR 2022)☆546Updated 2 years ago
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆373Updated last year
- Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"☆715Updated last year
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆876Updated 2 years ago
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch☆780Updated 4 months ago