SISReL/GRPO-Qwen-Qwen3-4B-dapo_math
Updated
SISReL PRO
SISReL
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 5 days ago
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information updated a model 17 days ago
SISReL/GRPO-Qwen-Qwen3-4B-dapo_math published a model 17 days ago
SISReL/GRPO-Qwen-Qwen3-4B-dapo_mathOrganizations
models 20
SISReL/math-SRPO-Qwen3-8B-think-off
Updated
SISReL/math-RLRT-CorrectOnly-Qwen3-4B-Base-0.5
Updated
SISReL/math-RLSD-Qwen3-8B-nothink
Updated
SISReL/math-RLRT-CorrectOnly-Qwen3-4B-Base
Updated
SISReL/math-RLSD-Qwen3-4B-Base
Updated
SISReL/math-RLRT-full-Qwen3-4B-Base
Updated
SISReL/math-GRPO-Qwen3-4B-Base
Updated
SISReL/math-SDPO-Qwen3-4B-Instruct
Updated
SISReL/math-GRPO-Entropy-0.05-Qwen3-8B-Base
Updated
datasets 0
None public yet