CoolFace
15 results

astrai

ASTRAI-labs /Pluto-Nano-1.0-Pretrain-v2 ASTRAI Pluto Nano 1.0 — Pretrain Mix (v2) Curated multilingual pretraining corpus (~50 GB parquet, ~12 B tokens after tokenization) used for ASTRAI Pluto Nano 1.0, a 1 B-total / 50 M-active MoE model with 64 k vocabulary and 5 target languages (EN, PT, ES, ZH, HI). v2 additions vs v1: OpenThoughts3 (CoT reasoning), openstax textbooks + peS2o (science), and reweighting for better balance. NOTE: factsense (openbmb) was used at training time but is not redistributed here due to its… See the full description on the dataset page: https://huggingface.co/datasets/ASTRAI-labs/Pluto-Nano-1.0-Pretrain-v2.tabulartext-generation10M<n<100M2 likes1k downloads3mo agoHugging FaceASTRAI-labs /Pluto-Nano-1.0-Pretrain ASTRAI Pluto Nano 1.0 — Pretrain Mix Curated multilingual pretraining corpus (~37 GB parquet, ~10 B tokens after tokenization) used for the base pretrain of ASTRAI Pluto Nano 1.0, a 1 B-total / 47 M-active MoE model with 64 k vocabulary and 5 target languages (EN, PT, ES, ZH, HI). Source mix Weight Category Source License Local subdir 30 % EN Web HuggingFaceFW/fineweb-edu (sample-350BT) ODC-BY 1.0 en_fineweb_edu/ 10 % EN Web HuggingFaceFW/fineweb-edu… See the full description on the dataset page: https://huggingface.co/datasets/ASTRAI-labs/Pluto-Nano-1.0-Pretrain.tabulartext-generation10M<n<100M1 likes10 downloads3mo agoHugging Facemahfuzh74 /astra_intent_v6text1K<n<10K0 likes3 downloads2y agoHugging Facetanishq9160 /ASTRA-Installer0 likes2 downloads2mo agoHugging Face