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 6 days ago
mrinaalarora/drylabsim updated a Space 7 days ago
mrinaalarora/textarena-wordle-env published a Space 8 days ago
mrinaalarora/drylabsimOrganizations
None yet