arxiv:2610.40564
Yuda Song
sfanm
AI & ML interests
None yet
Recent Activity
authored a paper 3 days ago
Training Foundation Models with a Single Algorithm upvoted a paper 3 days ago
Training Foundation Models with a Single Algorithm updated a dataset 4 days ago
sfanm/unified-xchange-publicOrganizations
models 48
sfanm/nl_tower_ckpts
Reinforcement Learning • Updated
sfanm/nltower-100m-sft-tw1X-e4lr05
Text Generation • 0.1B • Updated • 824
sfanm/nltower-100m-sft-tw1X-e4
Text Generation • 0.1B • Updated • 851
sfanm/nltower-100m-sft-tw1X-e2lr05
Text Generation • 0.1B • Updated • 845
sfanm/nltower-100m-sft-tw1X-e2
Text Generation • 0.1B • Updated • 823
sfanm/nltower-100m-sft-tw1X-e1lr05
Text Generation • 0.1B • Updated • 825
sfanm/nltower-100m-sft-tw1X-e1
Text Generation • 0.1B • Updated • 812
sfanm/nltower-100m-cpt128
Text Generation • 0.1B • Updated • 805
sfanm/nltower-100m-cpt64
Text Generation • 0.1B • Updated • 796
sfanm/nltower-100m-cpt32
Text Generation • 0.1B • Updated • 787
datasets 17
sfanm/nltower-results
Viewer • Updated • 13.9k • 106
sfanm/unified-xchange-public
Updated • 35
sfanm/nltower-traces-tw1X
Viewer • Updated • 796k • 110
sfanm/nltower-env
Viewer • Updated • 45.1k • 138
sfanm/nltower-rl-mixes
Viewer • Updated • 62.3k • 461
sfanm/unified-training
Viewer • Updated • 1 • 96 • 1
sfanm/gsm8k-boxed-b16r1k-val-dumps
Preview • Updated • 630
sfanm/d24-unified-midtrain-anchors
Viewer • Updated • 9.23M • 815
sfanm/d24-midtrain-olmo3-10b-wholedoc
Viewer • Updated • 19.4M • 5.06k
sfanm/d24-midtrain-olmo3-5b-wholedoc
Viewer • Updated • 10.2M • 354