BlinkDL

PENG Bo's repositories

RWKV-LM

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

Language:PythonApache-2.014110 137 261

ChatRWKV

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

Language:PythonApache-2.09509 92 121

AI-Writer

AI 写小说，生成玄幻和言情网文等等。中文预训练生成模型。采用我的 RWKV 模型，类似 GPT-2 。AI写作。RWKV for Chinese novel generation.

Language:PythonApache-2.03380 50 26

Hua

Hua is an AI image editor with Stable Diffusion (and more).

Apache-2.0363 13 22

RWKV-CUDA

The CUDA version of the RWKV language model ( https://github.com/BlinkDL/RWKV-LM )

Language:Cuda223 3 10

nanoRWKV

RWKV in nanoGPT style

Language:PythonMIT193 50

minGPT-tuned

A *tuned* minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Language:Jupyter NotebookMIT117 7 3

modded-nanogpt-rwkv

RWKV-7: Surpassing GPT

Language:PythonMIT98 10

fast.c

Prepare for DeekSeek R1 inference: Benchmark CPU, DRAM, SSD, iGPU, GPU, ... with efficient code.

Language:CApache-2.073 5 1

RWKV-v2-RNN-Pile

RWKV-v2-RNN trained on the Pile. See https://github.com/BlinkDL/RWKV-LM for details.

Language:PythonApache-2.067 4 1

LinearAttentionArena

Here we will test various linear attention designs.

Language:PythonApache-2.062 90

SmallInitEmb

LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence

Language:Python59 30

BookCNN

《深度卷积网络：原理与实践》现已在淘宝天猫京东当当发售. 这里是其中的代码下载.

Language:Jupyter Notebook56 4 4

WorldModel

Let us make Psychohistory (as in Asimov) a reality, and accessible to everyone. Useful for LLM grounding and games / fiction / business / finance / governance, and can align agents with human too.

Apache-2.039 100