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 about 9 hours ago
mrinaalarora/qwen3-1.7b-grpo-62s-4r-2run published a Space about 9 hours ago
mrinaalarora/qwen3-1.7b-grpo-62s-4r-2run updated a model about 9 hours ago
mrinaalarora/wordle-grpo-Qwen3-1.7BOrganizations
None yet
models 4
mrinaalarora/wordle-grpo-Qwen3-1.7B
Text Generation • 2B • Updated
mrinaalarora/Nanbeige4-3B-Cold-Start-Reasoning-LoRA-Opus-Epoch3
Text Generation • Updated • 33
mrinaalarora/nanbeige4-3b-cold-start-reasoning-lora-glm-12k
Text Generation • Updated • 30
mrinaalarora/Nanbeige4-3B-Cold-Start-Reasoning-LoRA
Text Generation • Updated • 28
datasets 0
None public yet