RWKV-Vibe / rwkv-flaLinks
Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton
☆38Updated this week
Alternatives and similar repositories for rwkv-fla
Users that are interested in rwkv-fla are comparing it to the libraries listed below
Sorting:
- ☆23Updated 6 months ago
- A large-scale RWKV v6, v7(World, PRWKV, Hybrid-RWKV) inference. Capable of inference by combining multiple states(Pseudo MoE). Easy to de…☆38Updated last week
- RWKV-X is a Linear Complexity Hybrid Language Model based on the RWKV architecture, integrating Sparse Attention to improve the model's l…☆42Updated this week
- ☆37Updated 2 months ago
- The WorldRWKV project aims to implement training and inference across various modalities using the RWKV7 architecture. By leveraging diff…☆52Updated last week
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28Updated 2 months ago
- BlackGoose Rimer: RWKV as a Superior Architecture for Large-Scale Time Series Modeling☆24Updated 3 weeks ago
- ☆134Updated 3 weeks ago
- This project is to extend RWKV LM's capabilities including sequence classification/embedding/peft/cross encoder/bi encoder/multi modaliti…☆10Updated 11 months ago
- ☆18Updated 6 months ago
- RWKV-7: Surpassing GPT☆92Updated 7 months ago
- GoldFinch and other hybrid transformer components☆45Updated 11 months ago
- ☆22Updated 3 weeks ago
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆32Updated 11 months ago
- 用户友好、开箱即用的 RWKV Prompts 示例，适用于所有用户。Awesome RWKV Prompts for general users, more user-friendly, ready-to-use prompt examples.☆35Updated 5 months ago
- Fast modular code to create and train cutting edge LLMs☆67Updated last year
- RWKV-LM-V7(https://github.com/BlinkDL/RWKV-LM) Under Lightning Framework☆35Updated this week
- Here we will test various linear attention designs.☆60Updated last year
- Reinforcement Learning Toolkit for RWKV.(v6,v7,ARWKV) Distillation,SFT,RLHF(DPO,ORPO), infinite context training, Aligning. Exploring the…☆47Updated last week
- MiSS is a novel PEFT method that features a low-rank structure but introduces a new update mechanism distinct from LoRA, achieving an exc…☆20Updated 3 weeks ago
- Official repository for ICML 2024 paper "MoRe Fine-Tuning with 10x Fewer Parameters"☆20Updated last month
- ☆33Updated 3 weeks ago
- Linear Attention Sequence Parallelism (LASP)☆85Updated last year
- A specialized RWKV-7 model for Othello(a.k.a. Reversi) that predicts legal moves, evaluates positions, and performs in-context search. It…☆41Updated 5 months ago
- State tuning tunes the state☆34Updated 5 months ago
- RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!☆148Updated 11 months ago
- RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best…☆49Updated 3 months ago
- ☆34Updated 11 months ago
- RWKV, in easy to read code☆72Updated 3 months ago
- continous batching and parallel acceleration for RWKV6☆24Updated last year