metadata
language:
- en
tags:
- pytorch
- text-generation
- causal-lm
- rwkv
license: apache-2.0
datasets:
- the_pile
RWKV-4 14B
Model Description
RWKV-4 14B is a L40-D5120 causal language model trained on the Pile. See https://github.com/BlinkDL/RWKV-LM for details.
Use https://github.com/BlinkDL/ChatRWKV to run it.
ctx_len = 1024 n_layer = 40 n_embd = 5120
Preview checkpoint: RWKV-4-Pile-14B-20230121-6210.pth : Trained on the Pile for 256B tokens.
- Pile loss 1.7746
- LAMBADA ppl 3.83, acc 70.79%
- PIQA acc 77.53%
- SC2016 acc 74.83%
- Hellaswag acc_norm 69.78%
- WinoGrande acc 63.54%