Phase 2: reasoning SFT Collection Reasoning SFT on 30K samples of OpenThoughts3 (OT30K) or another reasoning dataset, and the checkpoints each run starts from. • 104 items • Updated 2 days ago
open-sci/sft__ot30k_open-sci-ref-v0.02-1.7b-nemotron-hq-300B-4096-longsft_16k-DPO-Tulu3 Feature Extraction • 2B • Updated 3 days ago • 28
open-sci/sft__ot30k_open-sci-ref-v0.02-1.7b-nemotron-hq-300B-4096-longsft_16k-DPO-Tulu3 Feature Extraction • 2B • Updated 3 days ago • 28
open-sci/open-sci-ref-v0.02-1.7b-nemotron-hq-300B-4096-longsft_16k-SFT-Tulu3-decontaminated-sr30k Feature Extraction • 2B • Updated 3 days ago • 31
open-sci/open-sci-ref-v0.02-1.7b-nemotron-hq-300B-4096-longsft_16k-SFT-Tulu3-decontaminated-sr30k Feature Extraction • 2B • Updated 3 days ago • 31
open-sci/open-sci-ref-v0.02-1.7b-nemotron-hq-300B-4096-longsft_16k-SFT-Tulu3-decontaminated-nc30k Feature Extraction • 2B • Updated 3 days ago • 27
open-sci/open-sci-ref-v0.02-1.7b-nemotron-hq-300B-4096-longsft_16k-SFT-Tulu3-decontaminated-nc30k Feature Extraction • 2B • Updated 3 days ago • 27
open-sci/open-sci-ref-v0.02-1.7b-nemotron-hq-300B-4096-longsft_16k-SFT-Tulu3-decontaminated-ar30k Feature Extraction • 2B • Updated 3 days ago • 29
open-sci/open-sci-ref-v0.02-1.7b-nemotron-hq-300B-4096-longsft_16k-SFT-Tulu3-decontaminated-ar30k Feature Extraction • 2B • Updated 3 days ago • 29
Phase 2: reasoning SFT Collection Reasoning SFT on 30K samples of OpenThoughts3 (OT30K) or another reasoning dataset, and the checkpoints each run starts from. • 104 items • Updated 2 days ago