nkypy / candle-rwkv
RWKV models and examples powered by candle.
☆18Updated last month
Alternatives and similar repositories for candle-rwkv:
Users that are interested in candle-rwkv are comparing it to the libraries listed below
- A highly customizable, full scale web backend for web-rwkv, built on axum with websocket protocol.☆26Updated last year
- ☆32Updated 2 years ago
- A relatively basic implementation of RWKV in Rust written by someone with very little math and ML knowledge. Supports 32, 8 and 4 bit eva…☆93Updated last year
- Implementation of the RWKV language model in pure WebGPU/Rust.☆298Updated last week
- State tuning tunes the state☆32Updated 2 months ago
- ☆119Updated last week
- A converter and basic tester for rwkv onnx☆42Updated last year
- https://x.com/BlinkDL_AI/status/1884768989743882276☆27Updated 2 months ago
- RWKV centralised docs for the community☆22Updated 3 weeks ago
- RWKV in nanoGPT style☆189Updated 10 months ago
- RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!☆148Updated 8 months ago
- ☆130Updated 5 months ago
- Course Project for COMP4471 on RWKV☆17Updated last year
- This project is established for real-time training of the RWKV model.☆49Updated 11 months ago
- ☆44Updated 2 weeks ago
- RWKV, in easy to read code☆72Updated last month
- A high-performance constrained decoding engine based on context free grammar in Rust☆50Updated 3 months ago
- ☆19Updated 6 months ago
- Prepare for DeekSeek R1 inference: Benchmark CPU, DRAM, SSD, iGPU, GPU, ... with efficient code.☆71Updated 2 months ago
- Fast modular code to create and train cutting edge LLMs☆66Updated 11 months ago
- ☆18Updated 3 months ago
- A large-scale RWKV v6, v7(World, ARWKV, PRWKV) inference. Capable of inference by combining multiple states(Pseudo MoE). Easy to deploy o…☆35Updated this week
- Reinforcement Learning Toolkit for RWKV.(v6,v7,ARWKV) Distillation,SFT,RLHF(DPO,ORPO), infinite context training, Aligning. Exploring the…☆37Updated this week
- Trying to deconstruct RWKV in understandable terms☆14Updated last year
- Evaluating LLMs with Dynamic Data☆82Updated 2 months ago
- ☆13Updated last year
- ☆34Updated last month
- Training a reward model for RLHF using RWKV.☆14Updated last year
- Rust standalone inference of Namo-500M series models. Extremly tiny, runing VLM on CPU.☆24Updated last month
- BlinkDL's RWKV-v4 running in the browser☆47Updated 2 years ago