Text Generation
PyTorch
causal-lm
rwkv
rwkv-4-world / README.md
BlinkDL's picture
Update README.md
be0946a
|
raw
history blame
1.65 kB
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-4 World

Model Description

RWKV-4 trained on 100+ world languages (70% English, 15% multilang, 15% code).

Some_Pile + Some_RedPajama + Some_OSCAR + All_Wikipedia + All_ChatGPT_Data_I_can_find

How to use:

The differences between World & Raven:

  • set pipeline = PIPELINE(model, "rwkv_vocab_v20230424") instead of 20B_tokenizer.json (EXACTLY AS WRITTEN HERE. "rwkv_vocab_v20230424" is included in rwkv 0.7.4+)
  • use Question/Answer or User/AI or Human/Bot for chat. DO NOT USE Bob/Alice or Q/A

For 0.1/0.4/1.5B models, use fp32 for first layer (will overflow in fp16 at this moment - fixable in future), or bf16 if you have 30xx/40xx GPUs. Example strategy: cuda fp32 *1 -> cuda fp16

NOTE: the new greedy tokenizer (https://github.com/BlinkDL/ChatRWKV/blob/main/tokenizer/rwkv_tokenizer.py) will tokenize '\n\n' as one single token instead of ['\n','\n']

QA prompt (replace \n\n in xxx to \n):

Question: xxx

Answer:

and

Instruction: xxx

Input: xxx

Response:

A good chat prompt (replace \n\n in xxx to \n):

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: