Text Generation
English

ReFORM C10 Model

ReFORM is a reccurent transformer architecture based on RoPE Transformer that uses Huginn-like tricks mixed with RWKV and other stuff: token shifting, latent thinking vector, vector-mixing, etc.

So, it's ~10M model trained ~10 minutes on RTX 5070 TI.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Dataset used to train RedCatTeam/ReFORM-C10