ryusangwon/ko_en_qe_ppo_0.9_1e-6
Reinforcement Learning
•
Updated
•
2
Ryu Sangwon
ryusangwon
AI & ML interests
Text Generation, Writing Assistant, Summarization
Recent Activity
updated
a model
6 days ago
ryusangwon/ko_en_qe_ppo_0.9_1e-6
published
a model
6 days ago
ryusangwon/ko_en_qe_ppo_0.9_1e-6
updated
a model
6 days ago
ryusangwon/ko_en_qe_ppo_0.99_5e-6
Organizations
None yet
models
165
ryusangwon/ko_en_qe_ppo_0.99_5e-6
Reinforcement Learning
•
Updated
•
2
ryusangwon/ko_en_qe_ppo_0.99_5e-5
Reinforcement Learning
•
Updated
•
2
ryusangwon/ko_en_qe_ppo_0.99_1e-6
Reinforcement Learning
•
Updated
•
2
ryusangwon/ko_en_qe_ppo_1_1e-6
Reinforcement Learning
•
Updated
ryusangwon/ko_en_dpo_0.7_5e-7_val_ko_en_nllb-200-distilled-1.3B
Text2Text Generation
•
Updated
•
7
ryusangwon/ko_en_dpo_0.9_5e-7_ko_en_nllb-200-distilled-1.3B
Text2Text Generation
•
Updated
•
13
ryusangwon/ko_en_dpo_0.7_1e-6_ko_en_nllb-200-distilled-1.3B
Text2Text Generation
•
Updated
•
7
ryusangwon/ko_en_dpo_0.7_5e-7_ko_en_nllb-200-distilled-1.3B
Text2Text Generation
•
Updated
•
9
ryusangwon/ko_en_dpo_0.999_1e-6_ko_en_nllb-200-distilled-1.3B
Text2Text Generation
•
Updated
•
10
datasets
24
ryusangwon/hotpotqa_top5_atom_few_shot
Viewer
•
Updated
•
5
•
44
ryusangwon/hotpotqa_top5_500
Viewer
•
Updated
•
500
•
53
ryusangwon/hotpotqa_top5_atom
Viewer
•
Updated
•
5.41k
•
43
ryusangwon/nq_top5_atom
Viewer
•
Updated
•
3.61k
•
46
ryusangwon/nq_colbert_top5_atom
Viewer
•
Updated
•
3.61k
•
48
ryusangwon/qsaf_full_squad_no_answer_20
Viewer
•
Updated
•
39.6k
•
45
ryusangwon/nq_top5_atom_has_answer
Viewer
•
Updated
•
3.61k
•
39
ryusangwon/nq_top5_atom_few_shot
Viewer
•
Updated
•
5
•
56
ryusangwon/qsaf_full_squad_no_answer_10
Viewer
•
Updated
•
36.3k
•
45
ryusangwon/qsaf_full
Viewer
•
Updated
•
33k
•
42