Mrinaal Arora

mrinaalarora

·

https://aroramrinaal.com

AI & ML interests

AI alignment, AI safety, multilingual models and agent evaluation.

Recent Activity

liked a model about 1 month ago

rumik-ai/rumik-oss-1

updated a collection 3 months ago

Tiny Aya Emergent Misalignment

updated a collection 3 months ago

Tiny Aya Emergent Misalignment

View all activity

Organizations

None yet

New activity in humanitys-last-hackathon/signup 6 months ago

Update src/app/signup-panel.tsx

#1 opened 6 months ago by

New activity in mrinaalarora/Nanbeige4-3B-Cold-Start-Reasoning-LoRA-Opus-Epoch3 7 months ago

Update README.md

#1 opened 7 months ago by

New activity in mrinaalarora/nanbeige4-3b-cold-start-reasoning-lora-glm-12k 8 months ago

Update README.md

#1 opened 8 months ago by

New activity in mrinaalarora/Nanbeige4-3B-Cold-Start-Reasoning-LoRA 8 months ago

Update README.md

#1 opened 8 months ago by

New activity in bharatgenai/Param2-17B-A2.4B-Thinking 8 months ago

Clarification needed: pretrained-only or was SFT applied post pretraining?

#5 opened 8 months ago by