Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
☆4,769Jul 18, 2025Updated last year
Alternatives and similar repositories for lingua
Users that are interested in lingua are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A PyTorch native platform for training generative AI models☆5,799Updated this week
- Minimalistic large language model 3D-parallelism training☆2,836Updated this week
- Efficient Triton Kernels for LLM Training☆6,655Updated this week
- PyTorch native post-training library☆5,811Sep 9, 2026Updated last month
- Official inference framework for 1-bit LLMs☆40,904Jul 27, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,258Aug 22, 2025Updated last year
- NanoGPT (124M) in 90 seconds☆5,935Sep 28, 2026Updated 2 weeks ago
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆3,379Oct 6, 2026Updated last week
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,323Aug 26, 2025Updated last year
- Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.☆2,102Jul 29, 2024Updated 2 years ago
- Entropy Based Sampling and Parallel CoT Decoding☆3,431Nov 13, 2024Updated last year
- Train transformer language models with reinforcement learning.☆19,498Updated this week
- AllenAI's post-training codebase☆3,891Updated this week
- 🚀 Efficient implementations for emerging model architectures☆5,850Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Fully open reproduction of DeepSeek-R1☆26,478Oct 2, 2026Updated last week
- Tools for merging pretrained large language models.☆7,392Sep 12, 2026Updated last month
- Schedule-Free Optimization in PyTorch☆2,329Jul 28, 2026Updated 2 months ago
- Fast and memory-efficient exact attention☆25,121Updated this week
- Modeling, training, eval, and inference code for OLMo☆6,698Nov 24, 2025Updated 10 months ago
- Code for BLT research paper☆2,067Nov 3, 2025Updated 11 months ago
- A framework for few-shot evaluation of language models.☆14,192Sep 14, 2026Updated 3 weeks ago
- A bibliography and survey of the papers surrounding o1☆1,215Jul 7, 2026Updated 3 months ago
- Robust recipes to align language models with human and AI preferences☆5,693Sep 23, 2026Updated 2 weeks 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.
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆13,699Updated this week
- Muon is Scalable for LLM Training☆1,548Aug 3, 2025Updated last year
- Minimal reproduction of DeepSeek R1-Zero☆13,251Feb 27, 2026Updated 7 months ago
- Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We als…☆18,563May 19, 2026Updated 4 months ago
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆2,554Oct 6, 2026Updated last week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,837Updated this week
- Helpful tools and examples for working with flex-attention☆1,257Updated this week
- Tile primitives for speedy kernels☆3,748Sep 12, 2026Updated last month
- Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.☆22,049Apr 15, 2026Updated 5 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audi…☆11,210Sep 9, 2026Updated last month
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆10,081Oct 5, 2026Updated last week
- A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.☆6,908Dec 17, 2025Updated 9 months ago
- SGLang is a high-performance serving framework for large language models and multimodal models.☆37,037Updated this week
- PyTorch native quantization for training and inference☆3,002Updated this week
- Ongoing research training transformer models at scale☆18,122Updated this week
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,562Updated this week