|
--- |
|
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-5 World (Training in Progress) |
|
|
|
Use https://huggingface.co/BlinkDL/rwkv-4-world for best models. I am still training RWKV-5. |
|
|
|
Use rwkv pip package 0.8.7+ for RWKV-5 inference. |
|
|
|
## Model Description |
|
|
|
RWKV-5 trained on 100+ world languages (70% English, 15% multilang, 15% code). |
|
|
|
World = Some_Pile + Some_RedPajama + Some_OSCAR + All_Wikipedia + All_ChatGPT_Data_I_can_find |
|
|
|
Training: set --my_testing "r" for latest RWKV-LM |
|
|
|
Inference algorithm reference: https://github.com/BlinkDL/ChatRWKV/blob/main/RWKV_v5_demo.py |
|
|
|
0.1B world: |
|
|
|
RWKV-5 37% trained = LAMBADA ppl 18.1 acc 42.93% |
|
|
|
RWKV-4 100% trained = LAMBADA ppl 25.5 acc 36.29% |
|
|
