AIIRWKV / RWKV-RAG
RAG SYSTEM FOR RWKV
☆46Updated 5 months ago
Alternatives and similar repositories for RWKV-RAG:
Users that are interested in RWKV-RAG are comparing it to the libraries listed below
- ☆121Updated 3 weeks 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.☆34Updated 3 months ago
- Reinforcement Learning Toolkit for RWKV.(v6,v7,ARWKV) Distillation,SFT,RLHF(DPO,ORPO), infinite context training, Aligning. Exploring the…☆39Updated last week
- The WorldRWKV project aims to implement training and inference across various modalities using the RWKV7 architecture. By leveraging diff…☆44Updated last month
- ☆13Updated 4 months ago
- This project is established for real-time training of the RWKV model.☆49Updated 11 months ago
- This is an inference framework for the RWKV large language model implemented purely in native PyTorch. The official native implementation…☆128Updated 9 months ago
- ☆18Updated 4 months ago
- RWKV-RAG个人版☆18Updated last week
- rwkv finetuning☆36Updated last year
- ☆22Updated 4 months ago
- RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!☆148Updated 8 months ago
- Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton☆28Updated this week
- ☆82Updated 11 months ago
- VisualRWKV is the visual-enhanced version of the RWKV language model, enabling RWKV to handle various visual tasks.☆222Updated last month
- 更简单的微调，提供便捷脚本，微调说明☆33Updated last week
- ☆43Updated 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
- Direct Preference Optimization for RWKV, aiming for RWKV-5 and 6.☆11Updated last year
- Implementation of the RWKV language model in pure WebGPU/Rust.☆300Updated last week
- Inference RWKV with multiple supported backends.☆43Updated this week
- GLM Series Edge Models☆137Updated 2 months ago
- 使用langchain进行任务规划，构建子任务的会话场景资源，通过MCTS任务执行器，来让每个子任务通过在上下文中资源，通过自身反思探索来获取自身对问题的最优答案；这种方式依赖模型的对齐偏好，我们在每种偏好上设计了一个工程框架，来完成自我对不同答案的奖励进行采样策略☆29Updated 3 weeks ago
- ☆10Updated last year
- The all-in-one RWKV runtime box with embed, RAG, AI agents, and more.☆558Updated last month
- 大模型推理框架加速，让 LLM 飞起来☆18Updated 11 months ago
- ☆34Updated last week
- ✅4g GPU可用 | 简易实现ChatGLM单机调用多个计算设备（GPU、CPU）进行推理☆34Updated 2 years ago
- 基于RWKV模型的角色扮演，实际上是个改的妈都不认识的 RWKV_Role_Playing☆16Updated last year
- RWKV centralised docs for the community☆24Updated last month