kgrabko/JiRackDatasetWikipediaEn download history

kgrabko/JiRackDatasetWikipediaEn is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 32 times (19 in the last 7 days), and 158 times in total. It ranks #260,371 among datasets by monthly downloads.

💎 JiRack Base dataset for 1.5B model Dataset: the dataset formated for JiRack tokenizer . I recommend initializing the model with a 4K context window for initial stability, followed by scaling to 8K context using specialized JiRack 8K datasets. This two-stage approach ensures robust posit

Open kgrabko/JiRackDatasetWikipediaEn on Hugging Face

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