Yurun Yuan
RyanYr
AI & ML interests
None yet
Recent Activity
upvoted a paper about 4 hours ago
Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States upvoted a paper 6 days ago
POLCA: Stochastic Generative Optimization with LLM updated a model 6 days ago
RyanYr/slf-dstl_regular_Q2.5-1.5B-It_tooluse_OPDOrganizations
None yet
models 12
RyanYr/slf-dstl_regular_Q2.5-1.5B-It_tooluse_OPD
Updated
RyanYr/slf-dstl_regular_Q2.5-1.5B-It_science_OPD
Updated
RyanYr/slf-dstl_Q2.5-1.5B-It_science_OPD
Updated
RyanYr/slf-dstl_Q2.5-1.5B-It_tooluse_SFT
2B • Updated • 61
RyanYr/slf-dstl_Q2.5-1.5B-It_science_SFT
2B • Updated • 77
RyanYr/pg-dapo-qwen2.5math-1.5B-base-mbs256-n8_actor
Updated • 16
RyanYr/pg-dapo-qwen2.5math-1.5B-base-n8_actor
Updated • 37
RyanYr/grpo-dapo_offline-qwen2.5math-1.5B-base-mbs256-n8_actor
Updated • 23
RyanYr/grpo-dapo-01_offline-qwen2.5math-1.5B-base-mbs256-n8_actor
Updated • 23
RyanYr/pg-dapo-01_offline-qwen2.5math-1.5B-base-mbs256-n8_actor
Updated • 24
datasets 16
RyanYr/self-distill_tooluse
Viewer • Updated • 4.14k • 36
RyanYr/self-distill_science
Viewer • Updated • 3.18k • 42
RyanYr/grpo-dapo_offline-qwen2.5math-1.5B-base-mbs256-n8_actor_matheval
Updated • 137
RyanYr/grpo-dapo-qwen2.5math-1.5B-base-mbs256-n8_actor_matheval
Updated • 135
RyanYr/grpo-dapo-01_offline-qwen2.5math-1.5B-base-mbs256-n8_actor_matheval
Updated • 161
RyanYr/pg-dapo-01_offline-qwen2.5math-1.5B-base-mbs256-n8_actor_matheval
Updated • 223
RyanYr/pg-dapo_offline-qwen2.5math-1.5B-base-mbs256-n8_actor_matheval
Updated • 199
RyanYr/DAPO-Math-17k-offline
Viewer • Updated • 410k • 73
RyanYr/DAPO-Math-17k
Viewer • Updated • 17.4k • 17
RyanYr/Qwen2.5-Math-7B-Instruct_AIME24-4096-t0.7_SD42_matheval
Viewer • Updated • 30 • 6