metadata

language:
  - en
  - zh
  - de
  - fr
  - es
  - pt
  - ru
  - it
  - ja
  - ko
  - vi
  - ar
tags:
  - pytorch
  - text-generation
  - causal-lm
  - rwkv
license: apache-2.0
datasets:
  - EleutherAI/pile
  - togethercomputer/RedPajama-Data-1T

RWKV-5 World (Training in Progress)

Use https://huggingface.co/BlinkDL/rwkv-4-world for best models. I am still training RWKV-5.

Model Description

RWKV-5 trained on 100+ world languages (70% English, 15% multilang, 15% code).

World = Some_Pile + Some_RedPajama + Some_OSCAR + All_Wikipedia + All_ChatGPT_Data_I_can_find

Training: set --my_testing "r" for latest RWKV-LM

Inference: Use rwkv pip package 0.8.6+ for RWKV-5. Might overflow in fp16. Use fp32.

inference algorithm reference: https://github.com/BlinkDL/ChatRWKV/blob/main/RWKV_v5_demo.py