Hippocrene
/

recurrent-transformer-0.1b-e0.4b

Text Generation

recurrent-transformer

universal-transformer

adaptive-computation-time

Model card Files Files and versions

recurrent-transformer-0.1b-e0.4b / tokenizer /tokenizer.json

Hippocrene's picture

Adaptive-Recurrent (ACT) 110M: base + SFT, inference, bundled tokenizer, model code

6cc25d5 verified about 1 month ago

History Contribute Delete

1.36 MB

File too large to display, you can check the raw version instead.