RWKV-7 World
Use rwkv pip package 0.8.28+ for RWKV-7 inference: https://pypi.org/project/rwkv/
For developers: https://github.com/BlinkDL/RWKV-LM/tree/main/RWKV-v7
Chat demo: https://github.com/BlinkDL/ChatRWKV/blob/main/API_DEMO_CHAT.py
Model Description
RWKV-7 trained on 100+ world languages (80% English, 10% multilang, 10% code).
World-v3 = 3.1T tokens
World-v2.9 = subsampled 2T tokens
World-v2.8 = subsampled 1T tokens
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 !!!
!!! There should not be any space after your final ":" or you will upset the tokenizer and see non-English reponse !!!
!!! There should not be any space after your final ":" or you will upset the tokenizer and see non-English reponse !!!