yuunnn-w / RWKV_PytorchLinks
This is an inference framework for the RWKV large language model implemented purely in native PyTorch. The official native implementation is overly complex and lacks extensibility. Let's join the flexible PyTorch ecosystem and open-source it together!
☆128Updated 10 months ago
Alternatives and similar repositories for RWKV_Pytorch
Users that are interested in RWKV_Pytorch are comparing it to the libraries listed below
Sorting:
- ☆124Updated this week
- rwkv finetuning☆36Updated last year
- RAG SYSTEM FOR RWKV☆49Updated 6 months ago
- This project is established for real-time training of the RWKV model.☆49Updated last year
- ☆13Updated 5 months ago
- VisualRWKV is the visual-enhanced version of the RWKV language model, enabling RWKV to handle various visual tasks.☆226Updated this week
- Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton☆29Updated last week
- ☆18Updated 5 months ago
- ☆22Updated 5 months ago
- Reinforcement Learning Toolkit for RWKV.(v6,v7,ARWKV) Distillation,SFT,RLHF(DPO,ORPO), infinite context training, Aligning. Exploring the…☆42Updated 2 weeks ago
- The WorldRWKV project aims to implement training and inference across various modalities using the RWKV7 architecture. By leveraging diff…☆47Updated 2 weeks ago
- Inference RWKV with multiple supported backends.☆48Updated this week
- RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!☆147Updated 9 months ago
- Evaluating LLMs with Dynamic Data☆92Updated last week
- Inference RWKV v5, v6 and v7 with Qualcomm AI Engine Direct SDK☆67Updated last week
- continous batching and parallel acceleration for RWKV6☆24Updated 11 months ago
- ☆123Updated last year
- ☆10Updated last year
- This repo is an exploratory experiment to enable frozen pretrained RWKV language models to accept speech modality input. We followed the …☆50Updated 5 months ago
- 更简单的微调,提供便捷脚本,微调说明☆36Updated this week
- Get down and dirty with FlashAttention2.0 in pytorch, plug in and play no complex CUDA kernels☆105Updated last year
- A large-scale RWKV v6, v7(World, PRWKV, Hybrid-RWKV) inference. Capable of inference by combining multiple states(Pseudo MoE). Easy to de…☆35Updated this week
- Direct Preference Optimization for RWKV, aiming for RWKV-5 and 6.☆11Updated last year
- 实现Blip2RWKV+QFormer的多模态图文对话大模型,使用Two-Step Cognitive Psychology Prompt方法,仅3B参数的模型便能够出现类人因果思维链。对标MiniGPT-4,ImageBind等图文对话大语言模型,力求以更小的算力和资源实…☆38Updated last year
- State tuning tunes the state☆33Updated 3 months ago
- Triton Documentation in Chinese Simplified / Triton 中文文档☆71Updated last month
- ☆82Updated last year
- ☆79Updated last year
- ☆14Updated last week
- A 20M RWKV v6 can do nonogram☆14Updated 7 months ago