Mobius-RWKV-r6-12B / README.md
TimeMobius's picture
Update README.md
339f0ef verified
|
raw
history blame
1.53 kB
metadata
license: apache-2.0

This is a experimental model, yet it is the Most powerful RNN model in the world.

Mobius RWKV r6 chat 12B 16k

Mobius is a RWKV v6 arch chat model, benifit from Matrix-Valued States and Dynamic Recurrence

Introduction

Mobius is a RWKV v6 arch model, a state based RNN+CNN+Transformer Mixed language model pretrained on a certain amount of data. In comparison with the previous released Mobius, the improvements include:

  • Only 24G Vram to run this model locally with fp16;
  • Significant performance improvement;
  • Multilingual support ;
  • Stable support of 16K context length.
  • function call support ;

Usage

We encourage you use few shots to use this model, Desipte Directly use User: xxxx\n\nAssistant: xxx\n\n is really good too, Can boost all potential ability.

Recommend Temp and topp: 0.7 0.6/1 0.3/1.5 0.3/0.2 0.8

function call format: System: func xxxx

User: xxxx

Assistant: xxxx

Obersavtion: xxxx

Assistant: xxxx

More details

Mobius 12B 16k based on RWKV v6 arch, which is leading state based RNN+CNN+Transformer Mixed large language model which focus opensouce community

  • 10~100 trainning/inference cost reduce;
  • state based,selected memory, which mean good at grok;
  • community support.

requirements

24G vram to run fp16, 12G for int8, 6G for nf4 with Ai00 server.

Benchmark

Ceval: Cmmlu: