Kideng's picture

Kideng

Kideng

·

luo-li-ba-suo

AI & ML interests

Reinforcement Learning, Language Model

Recent Activity

upvoted an article 8 days ago

ChatML vs Harmony: Understanding the new Format from OpenAI 🔍

liked a dataset 4 months ago

hfl/ruozhiba_gpt4

liked a model 11 months ago

ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-F16

View all activity

Organizations

None yet

upvoted an article 8 days ago

Article

ChatML vs Harmony: Understanding the new Format from OpenAI 🔍

Aug 9, 2025

•

54

upvoted a collection over 1 year ago

Skywork-Reward-Data-Collection

Open-source preference datasets used to train the Skywork reward model series • 16 items • Updated 25 days ago • 21

upvoted a paper about 2 years ago

Self-Rewarding Language Models

Paper • 2401.10020 • Published Jan 18, 2024 • 152