seongyun_lee's picture

seongyun_lee

Seongyun

·

AI & ML interests

None yet

Recent Activity

published a model about 3 hours ago

Seongyun/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_sample_190k

published a model about 3 hours ago

Seongyun/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_code_code2

updated a model about 3 hours ago

Seongyun/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_code_code

View all activity

Organizations

Papers 7

arxiv:2412.03679

arxiv:2406.05761

arxiv:2405.17977

arxiv:2401.06591

models 302

Seongyun/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_sample_190k

Updated about 3 hours ago

Seongyun/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_code_code2

Updated about 3 hours ago

Seongyun/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_code_code

Text Generation • Updated about 3 hours ago

Seongyun/rlpvr-v1.7.3-small-full

Updated about 3 hours ago

Seongyun/rlpvr-v1.7.2-small-full

Updated about 4 hours ago

Seongyun/rlpvr-v1.7.1-small-full

Updated about 13 hours ago

Seongyun/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_pref_repetition_penalty

Text Generation • Updated about 13 hours ago

Seongyun/rlpvr-v1.7-small-full

Updated about 19 hours ago

Seongyun/ds_r1_distill_qwen_1.5b_grpo_pref

Updated 1 day ago

Seongyun/rlpvr-v1.6-small-full

Updated 2 days ago • 4

datasets 1

Seongyun/flan-zs-noopt-thought-aug

Updated Dec 22, 2024 • 121