facebookresearch / lingua
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
☆4,164Updated this week
Related projects ⓘ
Alternatives and complementary repositories for lingua
- Efficient Triton Kernels for LLM Training☆3,401Updated this week
- A native PyTorch Library for large model training☆2,586Updated last week
- Official inference framework for 1-bit LLMs☆10,977Updated this week
- Run PyTorch LLMs locally on servers, desktop and mobile☆3,360Updated this week
- NanoGPT (124M) quality in 7.8 8xH100-minutes☆965Updated this week
- PyTorch native finetuning library☆4,283Updated this week
- Entropy Based Sampling and Parallel CoT Decoding☆2,970Updated this week
- nanoGPT style version of Llama 3.1☆1,231Updated 3 months ago
- Tools for merging pretrained large language models.☆4,793Updated last week
- Training LLMs with QLoRA + FSDP☆1,418Updated this week
- Speech To Speech: an effort for an open-sourced and modular GPT4-o☆3,499Updated last week
- High-quality datasets, tools, and concepts for LLM fine-tuning.☆1,980Updated 2 weeks ago
- A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.☆5,082Updated this week
- Composable building blocks to build Llama Apps☆4,496Updated this week
- g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains☆3,864Updated last month
- Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"☆801Updated 2 months ago
- Agentic components of the Llama Stack APIs☆3,860Updated this week
- ☆1,907Updated last week
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,029Updated last week
- ☆920Updated this week
- PyTorch native quantization and sparsity for training and inference☆1,549Updated this week
- DataComp for Language Models☆1,150Updated 2 weeks ago
- Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.☆1,827Updated 3 months ago
- The n-gram Language Model☆1,337Updated 3 months ago
- ☆2,737Updated last month
- Run Mixtral-8x7B models in Colab or consumer desktops☆2,294Updated 7 months ago
- Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜☆865Updated 2 months ago
- 🤖 MLE-Agent: Your intelligent companion for seamless AI engineering and research. 🔍 Integrate with arxiv and paper with code to provide…☆1,088Updated this week
- Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors a…☆1,190Updated this week
- MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.☆1,121Updated this week