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 collection
2 days ago
Nanbeige4-3B Cold Start Reasoning LoRA Experiments updated
a collection
2 days ago
Nanbeige4-3B Cold Start Reasoning LoRA Experiments new activity
2 days ago
mrinaalarora/nanbeige4-3b-cold-start-reasoning-lora-glm-12k:Update README.md Organizations
None yet