Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts
Paper • 2608.20061 • Published • 46
mat-mul
mat-mul
AI & ML interests
None yet
Recent Activity
updated a model about 1 month ago
kakaocorp/kanana-2-30b-a3b-base updated a model about 1 month ago
kakaocorp/kanana-2-30b-a3b-instructOrganizations
upvoted a paper 8 days ago
updated 11
models about 1 month ago
kakaocorp/kanana-2-30b-a3b-base
Text Generation • 31B • Updated • 239 • 29
kakaocorp/kanana-2-30b-a3b-instruct
Text Generation • 31B • Updated • 942 • 47
kakaocorp/kanana-2-30b-a3b-thinking
Text Generation • 31B • Updated • 261 • 39
kakaocorp/kanana-2-30b-a3b-base-2601
Text Generation • 31B • Updated • 87 • 31
kakaocorp/kanana-2-30b-a3b-mid-2601
Text Generation • 31B • Updated • 79 • 31
kakaocorp/kanana-2-30b-a3b-instruct-2601
Text Generation • 31B • Updated • 11.2k • 57
kakaocorp/kanana-2-30b-a3b-thinking-2601
Text Generation • 31B • Updated • 617 • 62
kakaocorp/kanana-2-1.3b-instruct
Text Generation • 1B • Updated • 3.06k • 11
kakaocorp/kanana-2-3b-instruct
Text Generation • 4B • Updated • 8.58k • 11
kakaocorp/kanana-2-3b-base
Text Generation • 3B • Updated • 1.46k • 5
kakaocorp/kanana-2-1.3b-base
Text Generation • 1B • Updated • 10.6k • 6
published 4
models about 1 month ago
upvoted a collection about 2 months ago
kakaocorp/kanana-2-30b-a3b-thinking-2601
#7812 opened 7 months ago
by mat-mul
updated a
collection 7 months ago
updated a
collection 8 months ago