sungyub kim

sungyub

1 3 6

https://sungyubkim.github.io/

AI & ML interests

LLM

Recent Activity

liked a Space 4 days ago

FineEnvs/multi-harness-rl

updated a dataset 4 months ago

sungyub/deepscaler-preview-verl

new activity 6 months ago

sungyub/ifbench-verl:Hello, I find datatrove libarary doesn't have datatrove.utils.reward_score.ifeval

View all activity

Organizations

None yet

liked a Space 4 days ago

The ultimate guide to multi-harness RL

🔀

226

Train open models with RL inside real agent harnesses

liked a Space 7 months ago

The Synthetic Data Playbook: Generating Trillions of the Finest Tokens

📝

282

Explore synthetic data benchmarks with an interactive bookshelf

liked 2 Spaces 10 months ago

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

🍷

1.45k

Explore and download the FineWeb web‑scale text dataset

Evaluation Guidebook

📝

365

Explore LLM benchmark scores over time

liked 2 Spaces 11 months ago

The Ultra-Scale Playbook

🌌

4.08k

The ultimate guide to training LLM on large GPU Clusters

The Smol Training Playbook

📚

3.32k

The secrets to building world-class LLMs