SISReL PRO

SISReL

·

https://sisrel.kaist.ac.kr

sisrel

AI & ML interests

None yet

Recent Activity

updated a model 7 days ago

SISReL/REBUTTAL-math-ReverseRLSD-CorrectOnly-Qwen3-8B-nothink-run5-step50

published a model 7 days ago

SISReL/REBUTTAL-math-ReverseRLSD-CorrectOnly-Qwen3-8B-nothink-run5-step50

updated a model 2 months ago

SISReL/math-RLRTcorrect-RLSDincorrect-Qwen3-4B-Base-1.0

View all activity

Organizations

SISReL 's models 44

SISReL/REBUTTAL-math-ReverseRLSD-CorrectOnly-Qwen3-8B-nothink-run5-step50

8B • Updated 7 days ago • 16

SISReL/math-RLRTcorrect-RLSDincorrect-Qwen3-4B-Base-1.0

Updated Jun 4 • 1

SISReL/math-RLRTcorrect-RLSDincorrect-Qwen3-8B-Base-1.0

SISReL/math-ReverseRLSD-CorrectOnly-Qwen3-8B-nothink-0.5-decay-30

SISReL/math-RLSD-reprompt-Qwen3-4B-Base

SISReL/math-RLSD-csfooter-Qwen3-4B-Base

SISReL/code-SDPO-DeepSeek-R1-Distill-Qwen-7B-Think-Off-lcb-v5-train-v6-eval

SISReL/math-SDPO-template2-DeepSeek

SISReL/math-SDPO-DeepSeek-ref-think-tag-remove

SISReL/math-SDPO-DeepSeek-R1-Distill-Qwen-ref

SISReL/math-GRPO-DeepSeek

SISReL/math-GRPO-DeepSeek-Qwen-7B-len8192-2gpu

SISReL/math-SDPO-DeepSeek-Qwen-7B-new-reprompt-2

SISReL/math-SDPO-DeepSeek-Qwen-7B-len8192-2gpu-simple-prompt

SISReL/math-SDPO-DeepSeek-Qwen-7B-len8192-2gpu

SISReL/math-SDPO-DeepSeek-Qwen-7B-len2048-2gpu-simple-prompt

SISReL/math-SDPO-DeepSeek-Qwen-7B-len2048-2gpu

SISReL/math-GRPO-DeepSeek-Qwen-7B-len4096-2gpu

SISReL/math-GRPO-DeepSeek-Qwen-7B-len2048-2gpu

SISReL/math-GRPO-Qwen3-1.7B

SISReL/math-SDPO-Qwen3-1.7B

SISReL/DeepSeek-R1-Distill-Qwen-7B-solution-guided

Text Generation • 333k • Updated May 27 • 6

SISReL/math-SDPO-DeepSeek-Qwen-7B-len4096-simple-prompt

SISReL/math-GRPO-DeepSeek-Qwen-7B-len4096

SISReL/math-GRPO-DeepSeek-Qwen-7B-token-suppression

SISReL/GRPO-Qwen-Qwen3-4B-dapo_math

SISReL/math-SRPO-Qwen3-8B-think-off

SISReL/math-RLRT-CorrectOnly-Qwen3-4B-Base-0.5

SISReL/math-RLSD-Qwen3-8B-nothink

SISReL/math-RLRT-CorrectOnly-Qwen3-4B-Base