Jaegeun Han's picture

2 3

Jaegeun Han

haanjack

·

haanjack

AI & ML interests

LLM, LLM finetuning, Network Optimization, Hardware Acceleration

Recent Activity

upvoted an article 12 days ago

What is test-time compute and how to scale it?

upvoted an article 19 days ago

Open-source DeepResearch – Freeing our search agents

liked a dataset about 2 months ago

HuggingFaceFW/fineweb

View all activity

Organizations

models 15

haanjack/sd-class-butterflies-32

Updated Mar 12, 2023

haanjack/Reinforce-Pixelcopter-PLE-v0

Reinforcement Learning • Updated Mar 12, 2023

haanjack/dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning • Updated Mar 12, 2023 • 8

haanjack/rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning • Updated Mar 11, 2023

haanjack/ppo-LunarLander-v2-unit8

Reinforcement Learning • Updated Mar 11, 2023

haanjack/poca-SoccerTwos

Reinforcement Learning • Updated Mar 11, 2023 • 12

haanjack/a2c-PandaReachDense-v2

Reinforcement Learning • Updated Mar 11, 2023 • 4

haanjack/a2c-AntBulletEnv-v0

Reinforcement Learning • Updated Mar 11, 2023

haanjack/ppo-pyramids

Reinforcement Learning • Updated Mar 2, 2023 • 9

haanjack/ppo-SnowballTarget

Reinforcement Learning • Updated Mar 2, 2023 • 12

datasets

None public yet