Model checkpoints trained with varying LCCP token budgets, paper: “Don't Stop Long-Context Continual Pre-Training Too Early: An Empirical Scaling Law”
EdenQiao
EdenQiao
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Hinted Scaling Laws upvoted a paper 4 days ago
Democratizing Robot-Use Agents: A Unified Harness with Open Models updated a collection 15 days ago
Don't Stop LCCP!Organizations
None yet
models 12
EdenQiao/dont-stop-lccp-1.22b-32k-80n
1B • Updated
EdenQiao/dont-stop-lccp-1.22b-32k-40n
1B • Updated
EdenQiao/dont-stop-lccp-1.22b-32k-10n
Text Generation • Updated • 56
EdenQiao/dont-stop-lccp-1.22b-32k-120n
Updated
EdenQiao/Rethinking-Hybrid-Constraint
Updated
EdenQiao/Rethinking-Hybrid-S5-full-100b-32k-5b
Updated • 63
EdenQiao/Rethinking-Hybrid-S5-full-100b
Updated • 33
EdenQiao/Rethinking-Hybrid-S5-SWA-128-100b-32k-5b
Updated • 73
EdenQiao/Rethinking-Hybrid-S5-SWA-128-100b
Updated • 32
EdenQiao/Rethinking-Hybrid-S5-SWA-128-Nope-100b-32k-5b
Updated • 65