Tianjian Li's picture

1 7 9

Tianjian Li

dogtooth

·

https://tianjianl.github.io

truthbutcher

AI & ML interests

None yet

Recent Activity

liked a dataset 11 days ago

open-r1/Big-Math-RL-Verified-Processed

upvoted a paper 2 months ago

J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning

authored a paper 2 months ago

SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning

View all activity

Organizations

dogtooth 's datasets 218

dogtooth/llama31-8b-generated-classifier-scored-hs_1729485696

Viewer • Updated Oct 21, 2024 • 8.6k • 4

dogtooth/llama31-8b-generated-gold-scored-uf_1729070334-filtered-0.5

Viewer • Updated Oct 20, 2024 • 29.6k • 3

dogtooth/llama31-8b-generated-gold-scored-uf_1729070334-filtered-0.4

Viewer • Updated Oct 20, 2024 • 23.7k • 4

dogtooth/llama31-8b-generated-gold-scored-uf_1729070334-filtered-0.3

Viewer • Updated Oct 20, 2024 • 17.8k • 5

dogtooth/llama31-8b-generated-gold-scored-uf_1729070334-filtered-0.2

Viewer • Updated Oct 20, 2024 • 11.8k • 5

dogtooth/uf_llama3_8b_instruct_scored_gold_1728768289-filtered-0.1

Viewer • Updated Oct 20, 2024 • 1k • 4

dogtooth/llama31-8b-generated-gold-scored-ultrafeedback

Viewer • Updated Oct 16, 2024 • 59.2k • 8 • 1

dogtooth/llama31-8b-inst-uf-CHES-scored

Viewer • Updated Oct 16, 2024 • 61.1k • 14