Add Acknowledgement

Fix typo

Update README.md

total 250B tokens trained

Update README.md

Add 1.5B release model (trained with 2048 batch)

Update README.md

Update README.md

Update README.md

Add 1epoch model ckpt

Add bfloat16 weight, with 4.37M step trained

Add safetensors (100B) ckpt

Update README.md

Add 100B tokens ckpt

Update README.md

Add ~58B tokens ckpt

Merge branch 'main' of https://huggingface.co/beomi/KoRWKV-1.5B

Add 1.3M ckpt(= 42B tokens)

Update README.md

Update README.md

Add 956k step(=31.3B tokens) ckpt

RNN can extrapolate to Unlimited context

update to 810k step(~=26.5B tokens

edit weight keys

update

Add original ckpt for RWKV code

Update README.md

Merge branch 'main' of https://huggingface.co/beomi/KoRWKV-1.5B

Add 635k (20.8B tokens) step ckpt

Update README.md

Add 15.4B tokens(470k steps)

test

Update README.md

initial commit