Mark's picture

2 3 4

Mark

Makrrr

·

AI & ML interests

NLP, RLHF, IR

Recent Activity

upvoted a paper 17 days ago

Adaptation of Agentic AI

upvoted a paper 2 months ago

DeepSeek-OCR: Contexts Optical Compression

new activity 3 months ago

Makrrr/Qwen3-1.7B-GSM8K-GRPO-verl:Can we have the training setting?

View all activity

Organizations

liked a model 6 months ago

Makrrr/Qwen3-1.7B-GSM8K-GRPO-verl

Reinforcement Learning • 2B • Updated Jul 5, 2025 • 73 • 2

liked a Space 7 months ago

Check My Progress Deep RL Course

Check your progress in a Deep RL course

liked 2 Spaces 9 months ago

The Ultra-Scale Playbook

The ultimate guide to training LLM on large GPU Clusters

FineWeb: decanting the web for the finest text data at scale

Generate high-quality text data for LLMs using FineWeb