facebookresearch / chameleon
Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
☆1,823Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for chameleon
- Cambrian-1 is a family of multimodal LLMs with a vision-centric design.☆1,749Updated last week
- 4M: Massively Multimodal Masked Modeling☆1,600Updated last month
- Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation☆913Updated last week
- VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and…☆1,968Updated last week
- Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"☆801Updated 2 months ago
- Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation☆674Updated 3 months ago
- Mixture-of-Experts for Large Vision-Language Models☆1,971Updated 5 months ago
- A native PyTorch Library for large model training☆2,566Updated this week
- ☆2,815Updated 3 weeks ago
- Next-Token Prediction is All You Need☆1,786Updated 2 weeks ago
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,426Updated last week
- MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.☆1,117Updated this week
- PyTorch code and models for V-JEPA self-supervised learning from video.☆2,664Updated 3 months ago
- Reaching LLaMA2 Performance with 0.1M Dollars☆960Updated 3 months ago
- Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation☆1,297Updated 2 months ago
- nanoGPT style version of Llama 3.1☆1,229Updated 3 months ago
- A family of lightweight multimodal models.☆928Updated 2 weeks ago
- This repository provides the code and model checkpoints of the research paper: Scalable Pre-training of Large Autoregressive Image Model…☆696Updated 6 months ago
- DataComp for Language Models☆1,150Updated last week
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,333Updated 6 months ago
- VideoSys: An easy and efficient system for video generation☆1,761Updated this week
- DeepSeek-VL: Towards Real-World Vision-Language Understanding☆2,064Updated 6 months ago
- PyTorch native finetuning library☆4,267Updated this week
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,026Updated last week
- [ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation☆619Updated last month
- Codebase for Aria - an Open Multimodal Native MoE☆779Updated this week
- PyTorch native quantization and sparsity for training and inference☆1,541Updated this week
- The official implementation of Self-Play Fine-Tuning (SPIN)☆1,034Updated 6 months ago
- ICLR2024 Spotlight: curation/training code, metadata, distribution and pre-trained models for MetaCLIP; CVPR 2024: MoDE: CLIP Data Expert…☆1,245Updated 2 weeks ago