15 results

tiny_transformer

inall models datasets apps agents people projects

Datasets

All datasets matching “tiny_transformer”

N8Programs /arc-tiny-transformer-data ARC Tiny Transformer data Data and vote-level artifacts for N8python/arc-tiny-transformer. Corpus corpus/documents_3k_per_task.jsonl.zst is the exact pretraining corpus: 1,200,000 JSONL documents; 3,000 documents for each of 400 RE-ARC generator families; 3,401,127,124 ARC tokens; 10,413,648,837 uncompressed bytes; uncompressed SHA-256 5d1336f8d6f45358a377af2e3fd05d43c4bfe91621b0c6a44c53dad0e34ca430. Each record contains token IDs and metadata for task ID… See the full description on the dataset page: https://huggingface.co/datasets/N8Programs/arc-tiny-transformer-data.text-generation0 likes121 downloads1mo agoHugging Face