Yan Varakin
ZDPLI
AI & ML interests
All areas of NLP, computational mathematics, reinforcement learning, robotics.
Recent Activity
upvoted
an
article
4 days ago
StackLLaMA: A hands-on guide to train LLaMA with RLHF
upvoted
an
article
4 days ago
Fine-tune Llama 2 with DPO
upvoted
a
paper
4 days ago
Phi-4-reasoning Technical Report