The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”
☆1,001Jan 30, 2024Updated 2 years ago
Alternatives and similar repositories for Sophia
Users that are interested in Sophia are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆382Jun 4, 2024Updated 2 years ago
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,173Jan 11, 2024Updated 2 years ago
- [ICLR 2023] Eva: Practical Second-order Optimization with Kronecker-vectorized Approximation☆12Jul 31, 2023Updated 3 years ago
- 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch☆2,201Jul 9, 2026Updated last month
- QLoRA: Efficient Finetuning of Quantized LLMs☆11,009Jun 10, 2024Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆714Jan 26, 2026Updated 7 months ago
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793☆459May 13, 2025Updated last year
- Schedule-Free Optimization in PyTorch☆2,325Jul 28, 2026Updated last month
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,702Oct 28, 2024Updated last year
- maximal update parametrization (µP)☆1,754Jul 17, 2024Updated 2 years ago
- Foundation Architecture for (M)LLMs☆3,139Apr 11, 2024Updated 2 years ago
- ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning☆286Feb 27, 2023Updated 3 years ago
- LOMO: LOw-Memory Optimization☆993Jul 2, 2024Updated 2 years ago
- A PyTorch native platform for training generative AI models☆5,708Updated this week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Fast and memory-efficient exact attention☆24,856Updated this week
- Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models☆822Jun 8, 2025Updated last year
- Scaling Data-Constrained Language Models☆347Jun 28, 2025Updated last year
- RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable)…☆14,696Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆8,464Updated this week
- Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch☆655Dec 27, 2024Updated last year
- Fast & Simple repository for pre-training and fine-tuning T5-style models☆1,021Aug 21, 2024Updated 2 years ago
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"☆401Feb 24, 2024Updated 2 years ago
- LLM training code for Databricks foundation models☆4,443Mar 25, 2026Updated 5 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆7,267Jul 11, 2024Updated 2 years ago
- D-Adaptation for SGD, Adam and AdaGrad☆529Jan 22, 2025Updated last year
- Muon is an optimizer for hidden layers in neural networks☆2,823May 24, 2026Updated 3 months ago
- NanoGPT (124M) in 90 seconds☆5,764Aug 9, 2026Updated 3 weeks ago
- [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters☆5,914Mar 14, 2024Updated 2 years ago
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,545Updated this week
- Supercharge Your Model Training☆5,493Apr 29, 2026Updated 4 months ago
- 🚀 Efficient implementations for emerging model architectures☆5,710Updated this week
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆205May 30, 2026Updated 3 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities☆22,205Aug 26, 2026Updated last week
- Distributed K-FAC preconditioner for PyTorch☆98Sep 1, 2026Updated last week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,343Mar 6, 2025Updated last year
- A concise but complete full-attention transformer with a set of promising experimental features from various papers☆5,944Updated this week
- Cramming the training of a (BERT-type) language model into limited compute.☆1,366Jun 13, 2024Updated 2 years ago
- [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning☆668Jun 1, 2024Updated 2 years ago
- OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset☆7,529Jul 16, 2023Updated 3 years ago