oahzxl/ouro-stage4 download history

oahzxl/ouro-stage4 is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 23 times (7 in the last 7 days), and 23 times in total. It ranks #337,693 among datasets by monthly downloads.

ouro-stage4 Tokenized training data for mid-training ByteDance/Ouro-1.4B, built to the Stage 4 recipe of Ouro: Looped Language Models (arXiv:2510.25741, Section 4.2) at about 1/25 of the paper's scale. Everything here is token ids for the Ouro tokenizer (SmolLM family, vocabulary 49,1

Open oahzxl/ouro-stage4 on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.