metadata

language:
  - en
  - zh
  - fr
  - es
  - de
  - pt
  - ru
  - it
  - ja
  - ko
  - vi
  - ar
tags:
  - pytorch
  - text-generation
  - causal-lm
  - rwkv
license: apache-2.0
datasets:
  - cerebras/SlimPajama-627B
  - EleutherAI/pile
  - bigcode/starcoderdata
  - oscar-corpus/OSCAR-2301

RWKV-7 World

Use rwkv pip package 0.8.28+ for RWKV-7 inference: https://pypi.org/project/rwkv/

https://www.rwkv.com/

For developers: https://github.com/BlinkDL/RWKV-LM/tree/main/RWKV-v7

Model Description

RWKV-7 trained on 100+ world languages (80% English, 10% multilang, 10% code).

Recommended fine-tuning format (use \n for newlines):

User: xxxxxxxxxxxxxxx

Assistant: xxxxxxxxxxxxxxx
xxxxxxxxxxxxxxx
xxxxxxxxxxxxxxx

User: xxxxxxxxxxxxxxx
xxxxxxxxxxxxxxx

Assistant: xxxxxxxxxxxxxxx
xxxxxxxxxxxxxxx
xxxxxxxxxxxxxxx
xxxxxxxxxxxxxxx

A good chat prompt (better replace \n\n in xxx to \n, such that there will never be extra \n\n in response):

User: hi

Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.

User: xxx

Assistant:

QA prompt (better replace \n\n in xxx to \n, such that there will never be extra \n\n in response):

Question: xxx

Answer:

and

Instruction: xxx

Input: xxx

Response:

!!! There should not be any space after your final ":" or you will upset the tokenizer and see non-English reponse !!!