zeyi liao's picture

1 1 4

zeyi liao

lzy337

·

AI & ML interests

None yet

Recent Activity

new activity 5 days ago

open-r1/README:⚠️ Chat template foot gun with DeepSeek distilled models and RL format reward function

published a model 5 days ago

lzy337/DeepSeek-R1-Distill-Qwen-1.5B-GRPO

updated a model 6 days ago

lzy337/Qwen-2.5-7B-Simple-RL

View all activity

Organizations

models 3

lzy337/DeepSeek-R1-Distill-Qwen-1.5B-GRPO

Updated 5 days ago

lzy337/Qwen-2.5-7B-Simple-RL

Text Generation • Updated 6 days ago • 3

lzy337/Qwen2.5-1.5B-Open-R1-GRPO

Text Generation • Updated 7 days ago • 1

datasets 1

lzy337/attack_data_hf

Viewer • Updated Oct 24, 2023 • 1.2k • 278