202 8 4

Kyle Richardson

yakazimir

https://www.krichardson.me/

yakazimir

AI & ML interests

NLP, ML

Recent Activity

updated a dataset 2 days ago

yakazimir/on_policy_human_ai

upvoted a paper 2 days ago

Understanding the Logic of Direct Preference Alignment through Logic

published a dataset 3 days ago

yakazimir/on_policy_human_ai

View all activity

Organizations

Articles 1

Article

Introducing the Open Chain of Thought Leaderboard

Papers 43

models 10

datasets 14

yakazimir/on_policy_human_ai

Viewer • Updated 2 days ago • 92.5k • 8

yakazimir/preference_mixture

Viewer • Updated Feb 26 • 81.8k • 77

yakazimir/ultrafeedback_olmo1b_ref

Viewer • Updated Jan 14 • 62.5k • 26

yakazimir/mistral-instruct-ultrafeedback

Viewer • Updated Nov 14, 2024 • 62.7k • 17

yakazimir/ultrafeedback_binarized

Viewer • Updated Nov 14, 2024 • 63.1k • 121 • 1

yakazimir/llama3-ultrafeedback-armorm

Viewer • Updated Nov 14, 2024 • 61.8k • 21

yakazimir/preference_mix

Preview • Updated Sep 30, 2024 • 18

yakazimir/preference_alignment_ultra_cut

Viewer • Updated Sep 27, 2024 • 39.5k • 24

yakazimir/preference_tuning_hh_ultra

Viewer • Updated Sep 24, 2024 • 133k • 24

yakazimir/preference_alignment_total

Viewer • Updated Sep 22, 2024 • 153k • 19

Kyle Richardson

AI & ML interests

Recent Activity

Organizations

Articles 1

Introducing the Open Chain of Thought Leaderboard

Papers 43

models 10 Sort: Recently updated

datasets 14 Sort: Recently updated

models 10

datasets 14