facebookresearch / linguaLinks
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
☆4,565Updated 3 weeks ago
Alternatives and similar repositories for lingua
Users that are interested in lingua are comparing it to the libraries listed below
Sorting:
- NanoGPT (124M) in 3 minutes☆2,635Updated 2 weeks ago
- A PyTorch native platform for training generative AI models☆3,891Updated this week
- PyTorch native post-training library☆5,245Updated this week
- Everything about the SmolLM2 and SmolVLM family of models☆2,508Updated 2 months ago
- The simplest, fastest repository for training/finetuning small-sized VLMs.☆3,182Updated this week
- Code for BLT research paper☆1,680Updated 2 weeks ago
- AllenAI's post-training codebase☆2,997Updated this week
- Run PyTorch LLMs locally on servers, desktop and mobile☆3,590Updated 3 weeks ago
- ☆2,956Updated 8 months ago
- Efficient Triton Kernels for LLM Training☆5,178Updated this week
- nanoGPT style version of Llama 3.1☆1,373Updated 10 months ago
- Minimalistic 4D-parallelism distributed training framework for education purpose☆1,529Updated last week
- Large Concept Models: Language modeling in a sentence representation space☆2,220Updated 4 months ago
- Democratizing Reinforcement Learning for LLMs☆3,330Updated 3 weeks ago
- s1: Simple test-time scaling☆6,425Updated 3 weeks ago
- Recipes to scale inference-time compute of open models☆1,090Updated 3 weeks ago
- Entropy Based Sampling and Parallel CoT Decoding☆3,383Updated 6 months ago
- A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!☆1,074Updated 4 months ago
- Implementing DeepSeek R1's GRPO algorithm from scratch☆1,405Updated last month
- Tools for merging pretrained large language models.☆5,801Updated this week
- MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.☆1,302Updated last month
- Official inference framework for 1-bit LLMs☆19,979Updated last week
- 4M: Massively Multimodal Masked Modeling☆1,729Updated last week
- PyTorch native quantization and sparsity for training and inference☆2,088Updated this week
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆2,735Updated last week
- Training Large Language Model to Reason in a Continuous Latent Space☆1,138Updated 4 months ago
- Bringing BERT into modernity via both architecture changes and scaling☆1,394Updated 3 weeks ago
- Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜☆1,475Updated last week
- Minimalistic large language model 3D-parallelism training☆1,909Updated last week
- Sky-T1: Train your own O1 preview model within $450☆3,263Updated 3 weeks ago