Mark's picture

1 4

Mark

Makrrr

·

AI & ML interests

NLP, RLHF, IR

Recent Activity

updated a dataset 23 days ago

Makrrr/RolePred

published a dataset 23 days ago

Makrrr/RolePred

updated a model about 1 month ago

Makrrr/qwen3-8B-reasonmed-finetune-extreme

View all activity

Organizations

None yet

Makrrr 's models 13

Makrrr/qwen3-8B-reasonmed-finetune-extreme

Text Generation • 8B • Updated Jul 24 • 11

Makrrr/qwen2.5-7B-reasonmed-finetune-extreme

Text Generation • 8B • Updated Jul 23 • 8

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

Reinforcement Learning • 2B • Updated Jul 5 • 35 • 2

Makrrr/a2c-PandaReachDense-v3

Reinforcement Learning • Updated May 31

Makrrr/Pyramids

Reinforcement Learning • Updated May 30 • 3

Makrrr/ppo-SnowballTarget

Reinforcement Learning • Updated May 30

Makrrr/Pixelcopter-PLE-v0

Reinforcement Learning • Updated May 29

Makrrr/Cartpole-v1

Reinforcement Learning • Updated May 29

Makrrr/dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning • Updated May 28 • 2

Makrrr/QTable-Taxi-V3

Reinforcement Learning • Updated May 28

Makrrr/q-FrozenLake-v1-4x4-noSlippery

Reinforcement Learning • Updated May 28

Makrrr/ppo-Huggy

Reinforcement Learning • Updated May 27 • 5

Makrrr/ppo-LunarLander-v2

Reinforcement Learning • Updated May 27 • 1