J.L's starred repositories
efficient-kan
An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).
persona-hub
Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"
RWKV_LM_EXT
This project is to extend RWKV LM's capabilities including sequence classification/embedding/peft/cross encoder/bi encoder/multi modalities, etc.
uncheatable_eval
Evaluating LLMs with Dynamic Data
rwkv-tokenizer
A fast RWKV Tokenizer written in Rust
Megatron-LM
Ongoing research training transformer models at scale
RWKV-AlignBench
RWKV模型中文对齐评测结果
flash-linear-attention
Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton
Mat2Stencil
A Modular Matrix-Based DSL for Explicit and Implicit Matrix-Free PDE Solvers on Structured Grid.
RWKV-infctx-trainer
RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!
VisualRWKV
VisualRWKV is the visual-enhanced version of the RWKV language model, enabling RWKV to handle various visual tasks.
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
speech_dataset
The dataset of Speech Recognition