Two LoRA cold-start SFT experiments teaching structured think/answer reasoning to Nanbeige4-3B-Base using distilled traces from frontier models
Mrinaal Arora
mrinaalarora
AI & ML interests
None yet
Recent Activity
updated a Space 2 days ago
mrinaalarora/textarena-wordle-env updated a collection 14 days ago
Nanbeige4-3B Cold Start Reasoning LoRA Experiments new activity 14 days ago
mrinaalarora/Nanbeige4-3B-Cold-Start-Reasoning-LoRA-Opus-Epoch3:Update README.mdOrganizations
None yet