RWKV-v2-RNN-Pile Alternatives

Similar projects and alternatives to RWKV-v2-RNN-Pile

• RWKV-LM

  84 11,579 8.8 Python RWKV-v2-RNN-Pile VS 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.

• flash-attention

  26 10,642 9.4 Python RWKV-v2-RNN-Pile VS flash-attention

  Fast and memory-efficient exact attention

  

• WorkOS

  workos.com

  sponsored

  The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.

  

• RWKV-CUDA

  3 186 8.5 Cuda RWKV-v2-RNN-Pile VS RWKV-CUDA

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

• AI-Writer

  2 2,699 3.4 Python RWKV-v2-RNN-Pile VS 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.

• token-shift-gpt

  1 44 0.0 Python RWKV-v2-RNN-Pile VS token-shift-gpt

  Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing

• quality

  2 98 5.8 Python RWKV-v2-RNN-Pile VS quality

  

• SmallInitEmb

  1 41 3.2 Python RWKV-v2-RNN-Pile VS SmallInitEmb

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

• InfluxDB

  www.influxdata.com

  sponsored

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.