---
title: rwkv-5-world-ms
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/rwkv-5-world-ms"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/rwkv-5-world-ms.md"
repository: AI-ModelScope/rwkv-5-world-ms
last_updated: 2023-10-28
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
library_name:
  - pytorch
frameworks:
  - Pytorch
language:
  - en
  - zh
  - fr
  - es
  - de
  - pt
  - ru
  - it
  - ja
  - ko
  - vi
  - ar
downloads: 69
stars: 2
tags:
  - pytorch
  - text-generation
  - causal-lm
  - rwkv
---

# rwkv-5-world-ms

> rwkv-5-world-ms - AI-ModelScope 在 ModelScope 开源的模型。RWKV-5 World (Training in Progress)

AI-ModelScope/rwkv-5-world-ms 是 ModelScope 魔搭社区上的text-generation模型，采用 apache-2.0 许可。

- **Repository**: AI-ModelScope/rwkv-5-world-ms
- **License**: apache-2.0
- **Tasks**: text-generation
- **Tags**: pytorch, text-generation, causal-lm, rwkv
- **Downloads**: 69
- **Stars**: 2
- **Last updated**: 2023-10-28

Source: https://www.modelscope.cn/models/AI-ModelScope/rwkv-5-world-ms

---

# RWKV-5 World (Training in Progress)

## copy repo of https://huggingface.co/BlinkDL/rwkv-5-world

## I am now updating latest training-in-progress checkpts to https://huggingface.co/BlinkDL/temp/tree/main (to avoid bloating git history)

## I am now updating latest training-in-progress checkpts to https://huggingface.co/BlinkDL/temp/tree/main (to avoid bloating git history)

copy repo of https://huggingface.co/BlinkDL/rwkv-5-world

Use rwkv pip package 0.8.14+ for RWKV-5 inference: https://pypi.org/project/rwkv/



Online Demo: https://huggingface.co/spaces/BlinkDL/ChatRWKV-gradio

GUI: https://github.com/josStorer/RWKV-Runner (see Releases)

How it works: https://twitter.com/BlinkDL_AI/status/1685230712247795713

https://www.rwkv.com/

## Model Description

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

World = Some_Pile + Some_SlimPajama + Some_StarCoder + Some_OSCAR + All_Wikipedia + All_ChatGPT_Data_I_can_find

RWKV-5 training: set --my_testing "r2r4" in latest RWKV-LM v4neo: https://github.com/BlinkDL/RWKV-LM

World v1 = 0.59T tokens

World v2 = 1.12T tokens

Imagine what happens when we use more data :)