other models
#1
by
KnutJaegersberg
- opened
want to point you to two other interesting models to apply your secret sauce to, which have seen more tokens than pythia:
https://huggingface.co/mlfoundations/open_lm_1B
https://huggingface.co/KnutJaegersberg/RWKV-4-PilePlus-1B5-20230520-2942-486Gtokens-ctx4096