Updated open-sci-ref baselines. Re-training without dropout. Re-training on DCLM, FineWeb-Edu, Nemotron, HPLT-2, Pile. Further ref datasets included. • 3 items • Updated
No model card
- Downloads last month
- 4
Safetensors
Model size
2B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for open-sci/open-sci-ref-v0.02-1.7b-nemotron-hq-300B-16384-rope_theta-1M
Finetunes
2 models