bojone / FSQLinks
Keras implement of Finite Scalar Quantization
☆80Updated last year
Alternatives and similar repositories for FSQ
Users that are interested in FSQ are comparing it to the libraries listed below
Sorting:
- [ICCV 2025] SimVQ: Addressing Representation Collapse in Vector Quantized Models with One Linear Layer☆285Updated 7 months ago
- The official GitHub page for the survey paper "Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey". And this paper is unde…☆54Updated 2 weeks ago
- A Pytorch Implementation of Finite Scalar Quantization☆148Updated last year
- ☆196Updated last year
- ☆135Updated last year
- ☆28Updated last year
- LLaVA combines with Magvit Image tokenizer, training MLLM without an Vision Encoder. Unifying image understanding and generation.☆37Updated last year
- [ICCV 2023] Online Clustered Codebook☆176Updated 11 months ago
- ☆142Updated 4 months ago
- Implementation of Qformer from BLIP2 in Zeta Lego blocks.☆42Updated 9 months ago
- TensorFlow implementation of "Finite Scalar Quantization: VQ-VAE Made Simple" (ICLR 2024)☆20Updated last year
- LMM solved catastrophic forgetting, AAAI2025☆44Updated 4 months ago
- A torch-based implementation of K-Means and K-Means++☆17Updated 4 years ago
- ☆138Updated last year
- [ICLR 2023] Official implementation of Transnormer in our ICLR 2023 paper - Toeplitz Neural Network for Sequence Modeling☆79Updated last year
- Triton implement of bi-directional (non-causal) linear attention☆51Updated 6 months ago
- UnifiedMLLM: Enabling Unified Representation for Multi-modal Multi-tasks With Large Language Model☆22Updated last year
- Tiny-FSDP, a minimalistic re-implementation of the PyTorch FSDP☆72Updated this week
- Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.☆10Updated last year
- [ICML 2025 Spotlight] Direct Discriminative Optimization: Supercharging Diffusion/Autoregressive with GAN-type Discrimination☆95Updated 3 weeks ago
- AliTok: Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model☆44Updated last month
- Discrete Diffusion Forcing (D2F): dLLMs Can Do Faster-Than-AR Inference☆102Updated this week
- differentiable top-k operator☆22Updated 7 months ago
- [ICML'24 Oral] The official code of "DiJiang: Efficient Large Language Models through Compact Kernelization", a novel DCT-based linear at…☆102Updated last year
- Shortcut flow matching Pytorch implementation☆61Updated 7 months ago
- Official Pytorch Implementation of Our CVPR2023 Paper: "Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image…☆61Updated 2 years ago
- [ICLR 2025][arXiv:2406.07548] Image and Video Tokenization with Binary Spherical Quantization☆165Updated last year
- A repository for DenseSSMs☆88Updated last year
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆124Updated last week
- ☆45Updated 4 years ago