Seongryong Jung

SeongryongJung/Qwen3-8B-Tooluse-GRPO-TR

Text Generation • 8B • Updated 6 days ago • 47
SeongryongJung/Qwen3-8B-Tooluse-RLSD-TR

Text Generation • 8B • Updated 10 days ago • 196
SeongryongJung/Qwen3-8B-ToolUse-SDPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 14
SeongryongJung/Qwen3-8B-ToolUse-SRPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 19 • 1

Qwen3-8B Physics TR Methods

Qwen3-8B teacher-regularized RL method collection for the Physics dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-8B-Physics-GRPO-TR

Text Generation • 8B • Updated 10 days ago • 335
SeongryongJung/Qwen3-8B-Physics-RLSD-TR

Text Generation • 8B • Updated 10 days ago • 262
SeongryongJung/Qwen3-8B-Physics-SDPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 19
SeongryongJung/Qwen3-8B-Physics-SRPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 14

Qwen3-8B Biology TR Methods

Qwen3-8B teacher-regularized RL method collection for the Biology dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-8B-Biology-GRPO-TR

Text Generation • 8B • Updated 10 days ago • 284
SeongryongJung/Qwen3-8B-Biology-RLSD-TR

Text Generation • 8B • Updated 10 days ago • 293 • 1
SeongryongJung/Qwen3-8B-Biology-SDPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 17
SeongryongJung/Qwen3-8B-Biology-SRPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 20

Qwen3-4B Materials TR Methods

Qwen3-4B teacher-regularized RL method collection for the Materials dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-4B-Material-GRPO-TR

Text Generation • 4B • Updated 10 days ago • 204
SeongryongJung/Qwen3-4B-Material-RLSD-TR

Text Generation • 4B • Updated 10 days ago • 202
SeongryongJung/Qwen3-4B-Materials-SDPO-TR

Reinforcement Learning • 4B • Updated 10 days ago • 16
SeongryongJung/Qwen3-4B-Materials-SRPO-TR

Reinforcement Learning • 4B • Updated 10 days ago • 25

Qwen3-4B Chemistry TR Methods

Qwen3-4B teacher-regularized RL method collection for the Chemistry dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-4B-Chemical-GRPO-TR

Text Generation • 4B • Updated 11 days ago • 223
SeongryongJung/Qwen3-4B-Chemical-RLSD-TR

Text Generation • 4B • Updated 11 days ago • 200
SeongryongJung/Qwen3-4B-Chemistry-SDPO-TR

Reinforcement Learning • 4B • Updated 11 days ago • 54
SeongryongJung/Qwen3-4B-Chemistry-SRPO-TR

Reinforcement Learning • 4B • Updated 11 days ago • 18

Qwen3-4B Chemistry RL Fine-tuning

Qwen3-4B Chemistry checkpoints from the SciKnowEval-style generalization runs: GRPO baseline, RLSD, and SDPO.

SeongryongJung/Qwen3-4B-Chemistry-GRPO

Text Generation • 4B • Updated 11 days ago • 265
SeongryongJung/Qwen3-4B-Chemistry-RLSD

Text Generation • 4B • Updated 15 days ago • 42
SeongryongJung/Qwen3-4B-Chemistry-SDPO

Text Generation • 4B • Updated 15 days ago • 106 • 1

Qwen3-8B Materials TR Methods

Qwen3-8B teacher-regularized RL method collection for the Materials dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-8B-Material-GRPO-TR

Text Generation • 8B • Updated 10 days ago • 155
SeongryongJung/Qwen3-8B-Material-RLSD-TR

Text Generation • 8B • Updated 10 days ago • 163 • 1
SeongryongJung/Qwen3-8B-Materials-SDPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 20
SeongryongJung/Qwen3-8B-Materials-SRPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 13

Qwen3-8B Chemistry TR Methods

Qwen3-8B teacher-regularized RL method collection for the Chemistry dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-8B-Chemistry-GRPO-TR

Text Generation • 8B • Updated 10 days ago • 421
SeongryongJung/Qwen3-8B-Chemistry-RLSD-TR

Text Generation • 8B • Updated 10 days ago • 411
SeongryongJung/Qwen3-8B-Chemistry-SDPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 25
SeongryongJung/Qwen3-8B-Chemistry-SRPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 15

Qwen3-4B ToolUse TR Methods

Qwen3-4B teacher-regularized RL method collection for the ToolUse dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-4B-Tooluse-GRPO-TR

Text Generation • 4B • Updated 10 days ago • 204
SeongryongJung/Qwen3-4B-Tooluse-RLSD-TR

Text Generation • 4B • Updated 10 days ago • 205
SeongryongJung/Qwen3-4B-ToolUse-SDPO-TR

Reinforcement Learning • 4B • Updated 10 days ago • 19
SeongryongJung/Qwen3-4B-ToolUse-SRPO-TR

Reinforcement Learning • 4B • Updated 10 days ago • 17

Qwen3-4B Physics TR Methods

Qwen3-4B teacher-regularized RL method collection for the Physics dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-4B-Physics-GRPO-TR

Text Generation • 4B • Updated 11 days ago • 139
SeongryongJung/Qwen3-4B-Physics-RLSD-TR

Text Generation • 4B • Updated 11 days ago • 94
SeongryongJung/Qwen3-4B-Physics-SDPO-TR

Reinforcement Learning • 4B • Updated 11 days ago • 8
SeongryongJung/Qwen3-4B-Physics-SRPO-TR

Reinforcement Learning • 4B • Updated 11 days ago • 3

Qwen3-4B Biology TR Methods

Qwen3-4B teacher-regularized RL method collection for the Biology dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-4B-Biology-GRPO-TR

Text Generation • 4B • Updated 11 days ago • 59
SeongryongJung/Qwen3-4B-Biology-RLSD-TR

Text Generation • 4B • Updated 11 days ago • 141
SeongryongJung/Qwen3-4B-Biology-SDPO-TR

Reinforcement Learning • 4B • Updated 11 days ago • 16
SeongryongJung/Qwen3-4B-Biology-SRPO-TR

Reinforcement Learning • 4B • Updated 11 days ago • 12

OPSD

SeongryongJung/opsd-plain-8b

Updated Jun 8

Qwen3-8B ToolUse TR Methods

Qwen3-8B teacher-regularized RL method collection for the ToolUse dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-8B-Tooluse-GRPO-TR

Text Generation • 8B • Updated 6 days ago • 47
SeongryongJung/Qwen3-8B-Tooluse-RLSD-TR

Text Generation • 8B • Updated 10 days ago • 196
SeongryongJung/Qwen3-8B-ToolUse-SDPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 14
SeongryongJung/Qwen3-8B-ToolUse-SRPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 19 • 1

Qwen3-8B Materials TR Methods

Qwen3-8B teacher-regularized RL method collection for the Materials dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-8B-Material-GRPO-TR

Text Generation • 8B • Updated 10 days ago • 155
SeongryongJung/Qwen3-8B-Material-RLSD-TR

Text Generation • 8B • Updated 10 days ago • 163 • 1
SeongryongJung/Qwen3-8B-Materials-SDPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 20
SeongryongJung/Qwen3-8B-Materials-SRPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 13

Qwen3-8B Physics TR Methods

Qwen3-8B teacher-regularized RL method collection for the Physics dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-8B-Physics-GRPO-TR

Text Generation • 8B • Updated 10 days ago • 335
SeongryongJung/Qwen3-8B-Physics-RLSD-TR

Text Generation • 8B • Updated 10 days ago • 262
SeongryongJung/Qwen3-8B-Physics-SDPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 19
SeongryongJung/Qwen3-8B-Physics-SRPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 14

Qwen3-8B Chemistry TR Methods

Qwen3-8B teacher-regularized RL method collection for the Chemistry dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-8B-Chemistry-GRPO-TR

Text Generation • 8B • Updated 10 days ago • 421
SeongryongJung/Qwen3-8B-Chemistry-RLSD-TR

Text Generation • 8B • Updated 10 days ago • 411
SeongryongJung/Qwen3-8B-Chemistry-SDPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 25
SeongryongJung/Qwen3-8B-Chemistry-SRPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 15

Qwen3-8B Biology TR Methods

Qwen3-8B teacher-regularized RL method collection for the Biology dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-8B-Biology-GRPO-TR

Text Generation • 8B • Updated 10 days ago • 284
SeongryongJung/Qwen3-8B-Biology-RLSD-TR

Text Generation • 8B • Updated 10 days ago • 293 • 1
SeongryongJung/Qwen3-8B-Biology-SDPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 17
SeongryongJung/Qwen3-8B-Biology-SRPO-TR

Reinforcement Learning • 8B • Updated 10 days ago • 20

Qwen3-4B ToolUse TR Methods

Qwen3-4B teacher-regularized RL method collection for the ToolUse dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-4B-Tooluse-GRPO-TR

Text Generation • 4B • Updated 10 days ago • 204
SeongryongJung/Qwen3-4B-Tooluse-RLSD-TR

Text Generation • 4B • Updated 10 days ago • 205
SeongryongJung/Qwen3-4B-ToolUse-SDPO-TR

Reinforcement Learning • 4B • Updated 10 days ago • 19
SeongryongJung/Qwen3-4B-ToolUse-SRPO-TR

Reinforcement Learning • 4B • Updated 10 days ago • 17

Qwen3-4B Materials TR Methods

Qwen3-4B teacher-regularized RL method collection for the Materials dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-4B-Material-GRPO-TR

Text Generation • 4B • Updated 10 days ago • 204
SeongryongJung/Qwen3-4B-Material-RLSD-TR

Text Generation • 4B • Updated 10 days ago • 202
SeongryongJung/Qwen3-4B-Materials-SDPO-TR

Reinforcement Learning • 4B • Updated 10 days ago • 16
SeongryongJung/Qwen3-4B-Materials-SRPO-TR

Reinforcement Learning • 4B • Updated 10 days ago • 25

Qwen3-4B Physics TR Methods

Qwen3-4B teacher-regularized RL method collection for the Physics dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-4B-Physics-GRPO-TR

Text Generation • 4B • Updated 11 days ago • 139
SeongryongJung/Qwen3-4B-Physics-RLSD-TR

Text Generation • 4B • Updated 11 days ago • 94
SeongryongJung/Qwen3-4B-Physics-SDPO-TR

Reinforcement Learning • 4B • Updated 11 days ago • 8
SeongryongJung/Qwen3-4B-Physics-SRPO-TR

Reinforcement Learning • 4B • Updated 11 days ago • 3

Qwen3-4B Chemistry TR Methods

Qwen3-4B teacher-regularized RL method collection for the Chemistry dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-4B-Chemical-GRPO-TR

Text Generation • 4B • Updated 11 days ago • 223
SeongryongJung/Qwen3-4B-Chemical-RLSD-TR

Text Generation • 4B • Updated 11 days ago • 200
SeongryongJung/Qwen3-4B-Chemistry-SDPO-TR

Reinforcement Learning • 4B • Updated 11 days ago • 54
SeongryongJung/Qwen3-4B-Chemistry-SRPO-TR

Reinforcement Learning • 4B • Updated 11 days ago • 18

Qwen3-4B Biology TR Methods

Qwen3-4B teacher-regularized RL method collection for the Biology dataset. Includes GRPO-TR, RLSD-TR, SDPO-TR, and SRPO-TR models.

SeongryongJung/Qwen3-4B-Biology-GRPO-TR

Text Generation • 4B • Updated 11 days ago • 59
SeongryongJung/Qwen3-4B-Biology-RLSD-TR

Text Generation • 4B • Updated 11 days ago • 141
SeongryongJung/Qwen3-4B-Biology-SDPO-TR

Reinforcement Learning • 4B • Updated 11 days ago • 16
SeongryongJung/Qwen3-4B-Biology-SRPO-TR

Reinforcement Learning • 4B • Updated 11 days ago • 12

Qwen3-4B Chemistry RL Fine-tuning

Qwen3-4B Chemistry checkpoints from the SciKnowEval-style generalization runs: GRPO baseline, RLSD, and SDPO.

SeongryongJung/Qwen3-4B-Chemistry-GRPO

Text Generation • 4B • Updated 11 days ago • 265
SeongryongJung/Qwen3-4B-Chemistry-RLSD

Text Generation • 4B • Updated 15 days ago • 42
SeongryongJung/Qwen3-4B-Chemistry-SDPO

Text Generation • 4B • Updated 15 days ago • 106 • 1

OPSD

SeongryongJung/opsd-plain-8b

Updated Jun 8