torphix / infini-attentionLinks
Pytorch implementation of https://arxiv.org/html/2404.07143v1
☆21Updated last year
Alternatives and similar repositories for infini-attention
Users that are interested in infini-attention are comparing it to the libraries listed below
Sorting:
- Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs☆89Updated 10 months ago
- A Framework for Decoupling and Assessing the Capabilities of VLMs☆43Updated last year
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆136Updated last year
- [EMNLP 2024] RWKV-CLIP: A Robust Vision-Language Representation Learner☆141Updated 3 months ago
- [ICML'24] The official implementation of “Rethinking Optimization and Architecture for Tiny Language Models”☆123Updated 7 months ago
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆113Updated 3 months ago
- ☆74Updated last year
- Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Engines☆125Updated 9 months ago
- VisualRWKV is the visual-enhanced version of the RWKV language model, enabling RWKV to handle various visual tasks.☆233Updated 3 months ago
- Open-Pandora: On-the-fly Control Video Generation☆34Updated 9 months ago
- LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture☆210Updated 7 months ago
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks (EMNLP'24)☆147Updated 11 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
- imagetokenizer is a python package, helps you encoder visuals and generate visuals token ids from codebook, supports both image and video…☆35Updated last year
- FuseAI Project☆87Updated 7 months ago
- ☆95Updated 2 months ago
- Code for Paper: Harnessing Webpage Uis For Text Rich Visual Understanding☆53Updated 8 months ago
- ☆174Updated 6 months ago
- MiroMind-M1 is a fully open-source series of reasoning language models built on Qwen-2.5, focused on advancing mathematical reasoning.☆223Updated 3 weeks ago
- ☆29Updated last year
- ☆90Updated last year
- 最简易的R1结果在小模型上的复现，阐述类O1与DeepSeek R1最重要的本质。Think is all your need。利用实验佐证，对于强推理能力，think思考过程性内容是AGI/ASI的核心。☆43Updated 6 months ago
- Mixture-of-Experts (MoE) Language Model☆189Updated 11 months ago
- mllm-npu: training multimodal large language models on Ascend NPUs☆91Updated last year
- Our 2nd-gen LMM☆34Updated last year
- ☆79Updated 5 months ago
- SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama: https://arxiv.org/abs/2408.09333v2☆124Updated 9 months ago
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*☆106Updated 3 months ago
- ☆95Updated 3 weeks ago
- ☆69Updated 2 months ago