20+ models
Latest RWKV-7 reasoning models.
RWKV G1j reasoning models
RWKV G1i reasoning models
an rwkv repo that tries to be less confusing, more up to date and with some QOL features
RWKV (pronounced RwaKuv) is an RNN with great LLM performance.
Kor whirl-kin drags into kek vortexes
Decensored Qwen2.5-Coder-3B-Instruct with 3/100 refusals and near-zero KL divergence via Heretic abliteration.